Concrete raw material weighing system and method based on multi-stage discharging control strategy

Abstract

The invention relates to a concrete raw material weighing system and method based on a multistage discharging control strategy, and the system achieves the precise weighing of concrete raw materials through integrating a high-precision weighing sensor, a PLC controller, an electric actuator and an integrated sensor system. The system adopts a multi-stage discharging control strategy which comprises a high-speed discharging stage, a medium-speed discharging stage, a low-speed discharging stage and a single-particle discharging mode so as to adapt to different material characteristics and weighing requirements. And through an adaptive learning algorithm and an intelligent prediction model, discharging parameters can be dynamically adjusted, the material falling speed and weight can be predicted, and the weighing precision and stability can be improved. The technical bottleneck of traditional automatic equipment in coarse aggregate weighing is effectively solved, the concrete raw material detection efficiency and accuracy are improved, a new quality control tool is provided for the building industry, and the concrete raw material weighing device has important practical value and wide application prospects.

Description

Technical Field

[0001] The present invention relates to the technical field of weighing of concrete raw materials, and particularly to a concrete raw material weighing system and method based on a multi-stage discharging control strategy. Background Art

[0002] As one of the most widely used engineering materials in the construction industry, the quality of concrete is directly related to the safety, reliability and durability of building structures, and is the core of the quality of construction projects. In this context, the accurate weighing of concrete raw materials is particularly important, as it directly determines whether the concrete mix ratio is accurate, thus affecting the workability and final performance of the concrete. In this context, the development of a high-precision and highly adaptable concrete raw material weighing system has become an urgent need for the development of the industry.

[0003] Traditional weighing of concrete raw materials mainly relied on manual operation, but with the introduction of automation technology, automated weighing equipment has gradually replaced manual operation. These devices achieve automatic weighing of concrete raw materials through components such as high-precision weighing sensors and PLC controllers. However, when dealing with coarse aggregates with a relatively large single mass, existing automated weighing equipment faces significant technical challenges. Due to the irregular shape and large particle size of the coarse aggregates, it is particularly difficult to control the accuracy during the automated weighing process, and it is difficult to meet the requirements of high-precision weighing.

[0004] Existing automated weighing equipment has obvious technical bottlenecks in the accurate weighing of coarse aggregates. Specifically, when dealing with coarse aggregates, due to the relatively large single mass and irregular shape of the aggregates, it is easy for the weighing error to exceed the allowable range. In addition, the existing discharging control strategies of the equipment are relatively simple and cannot be adaptively adjusted according to the material characteristics, resulting in poor weighing continuity and stability. At the same time, there is a lack of an intelligent prediction model to predict the falling speed and weight of the material, and it is impossible to adjust the discharging strategy in advance to reduce the weighing error. These defects not only affect the quality of concrete, but also restrict the high-quality development of the construction industry. Summary of the Invention

[0005] In view of this, it is necessary to provide a concrete raw material weighing system and method based on a multi-stage discharging control strategy to solve the above-mentioned defects of the prior art.

[0006] To solve the above problems, in a first aspect, an embodiment of the present invention provides a concrete raw material weighing system based on a multi-stage discharging control strategy, including:

[0007] A silo for storing materials, a discharging port is provided at the bottom of the silo, and a hopper is arranged below the discharging port to receive the discharged materials;

[0008] A high-precision weighing sensor is installed at the bottom of the hopper and is connected to the PLC controller, which is used to monitor the material weight signal in real time and transmit it to the PLC controller;

[0009] The PLC controller is connected to the electric actuator and is used to generate control instructions according to the material weight signal and the preset multi-stage discharging control strategy;

[0010] The electric actuator is used to receive the control instructions of the PLC controller and adjust the opening degree of the discharging port to control the discharging speed.

[0011] Preferably, the multi-stage discharging control strategy includes:

[0012] Fast discharging stage: When the material weight obtained by the high-precision weighing sensor is less than the first weight threshold, the system discharges the material continuously at the preset discharging speed until the material weight reaches the first weight threshold;

[0013] Medium-speed discharging stage: When the material weight is greater than or equal to the first weight threshold and less than the second weight threshold, the system automatically reduces the discharging speed and continues to discharge the material until the material weight reaches the second weight threshold;

[0014] Slow discharging stage: When the material weight is greater than or equal to the second weight threshold and less than the third weight threshold, the system further reduces the discharging speed and discharges the material slowly until the material weight reaches the third weight threshold;

[0015] Single-particle discharging stage: When the material weight is greater than or equal to the third weight threshold and less than the target weight, the system switches to the single-particle discharging mode to precisely control the falling of each aggregate until the material weight reaches the target weight.

[0016] Preferably, the concrete raw material weighing system further includes:

[0017] An integrated sensor system is connected to the PLC controller; the integrated sensor system includes a speed sensor and an image recognition sensor;

[0018] The speed sensor is used to monitor the material falling speed in real time;

[0019] The image recognition sensor is used to obtain the particle size distribution, shape and volume of the material.

[0020] Preferably, the PLC controller integrates an adaptive learning algorithm, which is used to dynamically adjust the discharging parameters according to the real-time data fed back by the high-precision weighing sensor and the integrated sensor system; among them, the discharging parameters include the discharging speed and the opening degree of the discharging port;

[0021] Preferably, the PLC controller is also integrated with an intelligent prediction model, which is used to predict the falling speed and weight of the material in the next feeding stage according to the parameter characteristics of the material in the current feeding stage, so as to provide a decision basis for the adaptive learning algorithm.

[0022] In a second aspect, an embodiment of the present invention provides a method for weighing concrete raw materials of a concrete raw material weighing system based on a multi-stage feeding control strategy, including:

[0023] After calibrating and setting parameters for the concrete raw material weighing system, start the system;

[0024] The system adjusts the feeding speed in stages according to the real-time feedback material weight signal and the preset multi-stage feeding control strategy.

[0025] The PLC controller uses the integrated adaptive learning algorithm to dynamically adjust the feeding parameters according to the real-time data fed back by the high-precision weighing sensor and the integrated sensor system.

[0026] Preferably, the method further includes:

[0027] The PLC controller uses the integrated intelligent prediction model to predict the falling speed and material weight of the material in the next feeding stage according to the parameter characteristics of the material in the current feeding stage.

[0028] Preferably, the adaptive learning algorithm specifically includes:

[0029] Obtain the material weight collected by the high-precision weighing sensor, as well as the falling speed and particle size distribution of the material collected by the integrated sensor system; perform normalization processing on the obtained data;

[0030] Based on the normalized data, extract the feature vector X = [W ′ , v ′ , d ′ ; where X is the feature vector, and W’, v’ and d’ are the normalized material weight, material falling speed and particle size distribution respectively;

[0031] Use a neural network model for training; where the input of the neural network model is the feature vector X, and the output is the feeding parameters predicted by the model; the feeding parameters include the feeding speed and the opening degree of the feeding port;

[0032] During the training process, the gradient descent method is used to optimize the parameters of the neural network model, and the loss function is the mean square error between the feeding parameters predicted by the model and the actual optimal feeding parameters:

[0033]

[0034] In the formula, v pred,i and k pred,iThey are the discharging speed and the opening degree of the discharging port at the i-th discharging stage predicted by the model, respectively, v opt,i and k opt,i are the actual optimal discharging speed and the opening degree of the discharging port at the i-th discharging stage obtained through inverse calculation.

[0035] Preferably, the system adjusts the discharging speed in stages according to the real-time feedback of the material weight signal and the preset multi-stage discharging control strategy, including:

[0036] Fast discharging stage: When the material weight obtained by the high-precision weighing sensor is less than the first weight threshold, the system discharges the material continuously at the preset discharging speed until the material weight reaches the first weight threshold;

[0037] Medium-speed discharging stage: When the material weight is greater than or equal to the first weight threshold and less than the second weight threshold, the system automatically reduces the discharging speed and continues to discharge the material until the material weight reaches the second weight threshold;

[0038] Slow discharging stage: When the material weight is greater than or equal to the second weight threshold and less than the third weight threshold, the system further reduces the discharging speed and discharges the material slowly until the material weight reaches the third weight threshold;

[0039] Single-grain discharging stage: When the material weight is greater than or equal to the third weight threshold and less than the target weight, the system switches to the single-grain discharging mode and precisely controls the falling of each aggregate until the material weight reaches the target weight.

[0040] Preferably, in the single-grain discharging stage, the PLC controller uses the integrated intelligent prediction model to predict the material falling speed and the material weight when the next material falls;

[0041] The adaptive learning algorithm integrated in the PLC controller dynamically adjusts the discharging parameters according to the real-time weight signal feedback by the high-precision weighing sensor and the prediction result of the intelligent prediction model, so that the output of the electric actuator can precisely control the falling of each aggregate.

[0042] The concrete raw material weighing system and method based on the multi-stage discharging control strategy provided by the present invention have the following beneficial effects compared with the prior art:

[0043] 1) By adopting the high-precision weighing sensor and combining with the multi-stage discharging control strategy, the present invention realizes the precise weighing of concrete raw materials such as coarse aggregates. The weighing accuracy of the system is as high as ±0.05%.

[0044] 2) By integrating the adaptive learning algorithm and the intelligent prediction model, the present invention enables the system to dynamically adjust the discharging parameters according to the material characteristics, further improving the stability and continuity of weighing.

[0045] 3) When traditional automated equipment processes coarse aggregates, due to the relatively large single-piece mass and irregular shape of the aggregates, it is easy to cause the weighing error to exceed the allowable range. Through the multi-stage discharging control strategy and single-grain discharging mode, the present invention effectively solves the technical bottleneck in the weighing of coarse aggregates by traditional automated equipment, avoids the weighing error caused by the relatively large single-piece mass of coarse aggregates, improves the construction quality, reduces the project cost, and improves the construction efficiency, which has important practical application value for the construction of large-diameter pile foundations in karst areas. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 It is a schematic structural diagram of a concrete raw material weighing system based on a multi-stage discharging control strategy provided by the present invention;

[0047] Figure 2 It is a flowchart of a multi-stage discharging control strategy provided by the present invention;

[0048] Figure 3 It is a schematic diagram of the fast discharging stage provided by the present invention;

[0049] Figure 4 It is a schematic diagram of the medium-speed discharging stage provided by the present invention;

[0050] Figure 5 It is a schematic diagram of the slow discharging stage provided by the present invention;

[0051] Figure 6 It is a schematic diagram of the single-grain discharging stage provided by the present invention;

[0052] Figure 7 It is a schematic diagram of the collaborative work of the discharging port - integrated sensor system provided by the present invention;

[0053] Figure 8 It is a flowchart of a concrete raw material weighing method provided by the present invention;

[0054] Figure 9 It is a schematic diagram of the system operation interface provided by the present invention;

[0055] Figure 10 It is a schematic diagram of the data flow and optimization process of the adaptive learning algorithm provided by the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0056] The preferred embodiments of the present invention will be specifically described below with reference to the accompanying drawings. The accompanying drawings form a part of this application and are used together with the embodiments of the present invention to explain the principles of the present invention, rather than to limit the scope of the present invention.

[0057] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments can be included in at least one embodiment of the present application. The phrase occurs in various places in the specification and does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive of other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0058] Currently, existing automated weighing devices have obvious technical bottlenecks in the precise weighing of coarse aggregates. Specifically, when dealing with coarse aggregates, due to the relatively large single mass and irregular shape of the aggregates, it is easy to cause the weighing error to exceed the allowable range. In addition, the existing discharge control strategies of the devices are relatively simple and cannot be adaptively adjusted according to the material characteristics, resulting in poor weighing continuity and stability. At the same time, there is a lack of an intelligent prediction model to predict the falling speed and weight of the material, and it is impossible to adjust the discharge strategy in advance to reduce the weighing error. These defects not only affect the quality of concrete but also restrict the high-quality development of the construction industry.

[0059] In view of this, the present invention provides a method for weighing concrete raw materials based on a multi-stage discharge control strategy, aiming to achieve automatic and precise weighing of concrete raw materials by integrating high-precision weighing sensors, PLC controllers, electric actuators, and an integrated sensor system, combined with an adaptive learning algorithm and an intelligent prediction model. The system can dynamically adjust the discharge parameters, predict the falling behavior and weight of the material, effectively solve the accuracy problem of traditional devices in weighing coarse aggregates, improve the weighing accuracy and stability, meet the strict requirements of the construction industry for high-precision weighing, and enhance the quality and safety of construction projects. The following will be described and introduced through multiple embodiments.

[0060] Figure 1 FIG. is a schematic structural diagram of the concrete raw material weighing system based on the multi-stage discharge control strategy provided by the present invention. Referring to Figure 1 , the concrete raw material weighing system based on the multi-stage discharge control strategy provided by the present invention includes:

[0061] A silo for storing materials, a discharge port is provided at the bottom of the silo, and a hopper is arranged below the discharge port to receive the discharged materials;

[0062] A high-precision weighing sensor is installed at the bottom of the hopper and connected to the PLC controller, and is used for real-time monitoring of the material weight signal and transmitting it to the PLC controller;

[0063] The PLC controller is connected to the electric actuator and is used for generating control instructions according to the material weight signal and the preset multi-stage discharge control strategy;

[0064] An electric actuator is used to receive control instructions from a PLC controller and adjust the opening degree of the discharging port to control the discharging speed.

[0065] Specifically, referring to Figure 1 , the silo is used to store concrete raw materials. The design of the silo takes into account the stability of continuous feeding. In this embodiment, to meet the volume requirement of 130L, the silo can be designed as a cylindrical structure with a diameter of 1.2 meters and a height of 1.0 meter. The total capacity is slightly larger than 130L to ensure the stability of continuous feeding. A discharging port is provided at the bottom of the silo and is used in conjunction with a high-precision weighing sensor to achieve real-time monitoring of the material weight. The discharging port can be designed as a conical structure with an inner diameter of 100 mm and an outer diameter of 120 mm at the narrowest part to facilitate the smooth flow of materials. A material cylinder is arranged below the discharging port, and the material cylinder is used to receive the discharged materials. Observation windows and operation ports can be installed on the side of the silo to facilitate operators' daily inspections and maintenance.

[0066] The high-precision weighing sensor is one of the core components of the system. The high-precision weighing sensor used in this embodiment has a measuring range of 40 to 50 kg and an accuracy of up to 2 g to 5 g, ensuring that the error is strictly controlled within 0.5% when weighing 20 kg of materials. The sensor adopts advanced bridge strain gauge technology and detects weight changes in real time by precisely measuring resistance changes. Even under extreme conditions such as rapid discharging and material impact, it can provide stable and reliable readings. To further optimize the weighing process, the high-precision weighing sensor works closely with the PLC controller. By adjusting the discharging speed in real time, it effectively reduces the impact of the falling impulse of the material on the measurement result and ensures the smooth falling of the material. The weighing sensor is connected to the material cylinder through a connecting piece, and the weighing sensor can be finely adjusted in the horizontal direction to effectively compensate for the slight movement of the silo or the material cylinder, ensuring that the sensor reading only reflects the vertical load and avoiding lateral force interference, thereby greatly improving the accuracy and reliability of the weighing result. Through these designs and functions, the high-precision weighing sensor can provide accurate weight feedback, adapt to various industrial environments, and ensure the high precision and high reliability of the concrete raw material weighing system.

[0067] The PLC controller (Programmable Logic Controller) serves as the core control unit of the system and plays a crucial role in precisely managing the entire discharging process. It is responsible for receiving accurate weight signals from high-precision weighing sensors in real time and, based on preset control algorithms, quickly and accurately generating control instructions. The PLC controller features excellent high-speed data processing capabilities, enabling it to rapidly process a large amount of data from sensors and perform seamless data exchange with electric actuators and integrated sensor systems within the system through various communication interfaces, ensuring the real-time and accuracy of information transmission. The PLC controller is built with a large-capacity program memory for storing complex control algorithms and operation programs, which can guarantee the precision and repeatability of the weighing process. By outputting accurate control signals to electric actuators, the PLC controller can adjust the opening degree of the discharging port in real time, thereby precisely controlling the discharging speed and ensuring that the material is accurately discharged according to the predetermined target weight.

[0068] The electric actuator serves as a key execution component of the system and undertakes the important task of precisely controlling the opening degree of the discharging port to meet different weighing requirements. The electric actuator closely receives control instructions from the PLC controller and dynamically and flexibly adjusts the opening degree of the discharging port based on real-time weighing data and preset discharging curves, thereby ensuring that the material can fall precisely at a predetermined speed. This precise speed control mechanism is crucial for maintaining the stability and accuracy of the weighing process. When dealing with concrete raw materials with different characteristics and particle sizes, the electric actuator has strong adaptability. Whether it is rapid discharging to quickly approach the target weight or slow and precise discharging to ensure the final weighing accuracy, the electric actuator can handle it. In addition, the adjustment range of the electric actuator is wide, enabling it to adapt to various discharging conditions from high speed to low speed and ensuring fine regulation of the material flow rate throughout the discharging process.

[0069] The discharging port is used to achieve precise material discharge. In this embodiment, the discharging port is equipped with electric or pneumatic valves, which are controlled by electric actuators. The design of these valves can withstand the pressure and wear generated by concrete raw materials during the discharging process while ensuring reliable sealing performance to prevent material leakage or spillage. The opening and closing operations of the discharging port are directly controlled by the PLC controller to ensure synchronization with the material weight monitored by the weighing sensor and the discharging speed adjusted by the electric actuator, achieving precise material discharge. The electric or pneumatic valves have fast response characteristics and can complete the opening and closing actions within a short time, which is crucial for controlling the accuracy of the discharging process. The opening degree of the valves can be precisely adjusted according to the instructions of the PLC controller to meet different discharging requirements and material characteristics. In addition, the design of the discharging port also takes into account the convenience of maintenance and cleaning, facilitating necessary inspections and maintenance after long-term operation to ensure the long-term stable operation of the system.

[0070] Figure 2 This is a flowchart of the multi-stage discharging control strategy provided by the present invention. In a preferred embodiment of the present invention, the multi-stage discharging control strategy preset in the PLC controller includes:

[0071] Fast discharging stage: When the material weight obtained by the high-precision weighing sensor is less than the first weight threshold, the system continuously discharges the material at a preset discharging speed until the material weight reaches the first weight threshold; Figure 3 This is a schematic diagram of the fast discharging stage provided by the present invention.

[0072] Medium-speed discharging stage: When the material weight is greater than or equal to the first weight threshold and less than the second weight threshold, the system automatically reduces the discharging speed and continues to discharge the material until the material weight reaches the second weight threshold; Figure 4 This is a schematic diagram of the medium-speed discharging stage provided by the present invention.

[0073] Slow discharging stage: When the material weight is greater than or equal to the second weight threshold and less than the third weight threshold, the system further reduces the discharging speed and slowly discharges the material until the material weight reaches the third weight threshold; Figure 5 This is a schematic diagram of the slow discharging stage provided by the present invention.

[0074] Single-particle discharging stage: When the material weight is greater than or equal to the third weight threshold and less than the target weight, the system switches to the single-particle discharging mode and precisely controls the falling of each aggregate until the material weight reaches the target weight; Figure 6 This is a schematic diagram of the single-particle discharging stage provided by the present invention.

[0075] Specifically, referring to Figure 2 , in this embodiment, the first weight threshold, the second weight threshold, and the third weight threshold are set to 90% of the target weight, 95% of the target weight, and 99% of the target weight respectively. In the fast discharging stage, the system discharges the material at a higher speed to 90% of the target weight. In the medium-speed discharging stage, the system reduces the discharging speed and continues to discharge the material to 95% of the target weight. In the slow discharging stage, the system further reduces the discharging speed and slowly discharges the material to 99% of the target weight. At this time, the system switches to the single-particle discharging mode and precisely controls the falling of each aggregate until the material weight reaches the target weight.

[0076] By adopting a high-precision weighing sensor and combining with a multi-stage discharging control strategy, the present invention realizes the precise weighing of concrete raw materials such as coarse aggregates. The weighing accuracy of the system is as high as ±0.05%.

[0077] In a preferred embodiment of the present invention, the concrete raw material weighing system further includes:

[0078] An integrated sensor system, connected to the PLC controller; the integrated sensor system includes a speed sensor and an image recognition sensor;

[0079] The speed sensor is used to monitor the falling speed of the material in real time;

[0080] The image recognition sensor is used to obtain the particle size distribution, shape and volume of the material.

[0081] Specifically, referring to Figure 1 , the integrated sensor system, composed of a speed sensor and an image recognition sensor, is used to monitor and control the discharging process. The speed sensor measures the falling speed of the material in real time and provides dynamic data of the material flow for the PLC controller. The image recognition sensor captures images and analyzes the distribution, shape and volume of the material to ensure accurate assessment and control of the material flow state. The core task of the integrated sensor system is to predict the total mass in the current discharging process, including the material that has fallen on the high-precision weighing sensor and is stationary and the material still in the air, to ensure that the discharged material quantity is strictly controlled within the quality control error range. Based on the data collected by these sensors, the PLC controller can adjust the discharging parameters, such as the discharging speed and the opening degree of the discharging port, in real time, thereby optimizing the discharging process, reducing the weighing error, improving the weighing accuracy of the system, and ensuring the accuracy and reliability of the weighing of concrete raw materials. Figure 7 This is a schematic diagram of the collaborative work of the discharging port - integrated sensor system provided by the present invention.

[0082] Referring to Figure 7 , the PLC controller works in cooperation with the integrated sensor system to achieve real-time monitoring and precise control of the discharging process, reduce the manual operation error, and improve the weighing stability and repeatability.

[0083] In a preferred embodiment of the present invention, referring to Figure 1 , the PLC controller integrates an adaptive learning algorithm, which is used to dynamically adjust the discharging parameters according to the real-time data fed back by the high-precision weighing sensor and the integrated sensor system; wherein, the discharging parameters include the discharging speed and the opening degree of the discharging port.

[0084] In a preferred embodiment of the present invention, referring to Figure 1 , the PLC controller also integrates an intelligent prediction model, which is used to predict the falling speed and weight of the material in the next discharging stage according to the parameter characteristics of the material in the current discharging stage, and provide a decision-making basis for the adaptive learning algorithm.

[0085] The high-precision concrete raw material weighing system provided by the present invention has the following advantages:

[0086] (1) High measurement accuracy: The high-precision weighing sensor 2 adopted by the system ensures that the weighing accuracy reaches ±0.05%, meeting the requirements of the "Code for Acceptance of Construction Quality of Concrete Structures" (GB50204 - 2015), and improving the accuracy of the weighing of concrete raw materials.

[0087] (2) Automatic control: The PLC controller 3 works in coordination with the integrated sensor system 6 to achieve real-time monitoring and precise control of the discharging process, reduce human operation errors, and improve weighing stability and repeatability.

[0088] (3) Strong adaptability: The adaptive learning algorithm automatically optimizes the discharging parameters to adapt to different material characteristics, improves the adaptability and weighing accuracy of the system, and ensures the reliability of long-term operation.

[0089] (4) Easy to operate: The system has a user-friendly interface, is easy to operate, reduces the operation difficulty, improves work efficiency, and realizes the automation and intelligence of weighing concrete raw materials.

[0090] (5) Environmental adaptability: All components are designed with dust-proof, waterproof and anti-interference features to ensure the stability and durability of the system in various industrial environments, and guarantee long-term stable operation.

[0091] Figure 8 The flowchart of the method for weighing concrete raw materials provided by the present invention is referred to Figure 8 , and the method at least includes:

[0092] Step S1, after calibrating and setting parameters for the concrete raw material weighing system, start the system;

[0093] In actual operation, before executing step S1, first build the system, install the silo, and ensure that the bottom discharge port of the silo is aligned with the measurement platform of the high-precision weighing sensor, with an error not exceeding ±1 mm. Install the high-precision weighing sensor and perform initial calibration to ensure its measurement accuracy reaches ±0.05%. Install the PLC controller, electric actuator, and integrated sensor system in appropriate positions, and ensure that the connections between all components are correct.

[0094] In step S1, the system calibration process includes: Before starting the system, it is necessary to program the PLC controller to set key parameters such as the initial discharging speed and valve opening. These parameters are the basis for the system to discharge materials according to the preset multi-stage discharging control strategy.

[0095] Set the electric actuator, which is responsible for adjusting the opening of the discharging port to control the discharging speed. During the system calibration stage, it is necessary to ensure that the electric actuator can accurately respond to the instructions of the PLC controller and precisely control the opening of the discharging port.

[0096] Calibrate the integrated sensor system: Calibrate the speed sensor and image recognition sensor to ensure that they can accurately measure the falling speed and distribution of materials. The performance of the sensors such as sensitivity and accuracy can be tested and adjusted to ensure that they can provide reliable data support in actual operation.

[0097] After completing system calibration and parameter settings, start the system, Figure 9 which is a schematic diagram of the system operation interface provided by the present invention.

[0098] Step S2, the system adjusts the feeding speed in stages according to the real-time feedback material weight signal and the preset multi-stage feeding control strategy.

[0099] Specifically, the multi-stage feeding control strategy in this embodiment divides the feeding process into the following four stages:

[0100] Fast feeding stage: When the material weight obtained by the high-precision weighing sensor is less than the first weight threshold, the system continuously feeds at the preset feeding speed until the material weight reaches the first weight threshold;

[0101] Medium feeding stage: When the material weight is greater than or equal to the first weight threshold and less than the second weight threshold, the system automatically reduces the feeding speed and continues to feed until the material weight reaches the second weight threshold;

[0102] Slow feeding stage: When the material weight is greater than or equal to the second weight threshold and less than the third weight threshold, the system further reduces the feeding speed and slowly feeds until the material weight reaches the third weight threshold;

[0103] Single-grain feeding stage: When the material weight is greater than or equal to the third weight threshold and less than the target weight, the system switches to the single-grain feeding mode to precisely control the falling of each aggregate until the material weight reaches the target weight.

[0104] In a preferred embodiment of the present invention, in the single-grain feeding stage, the PLC controller uses the integrated intelligent prediction model to predict the material falling speed and material weight when the next material falls. The adaptive learning algorithm integrated in the PLC controller dynamically adjusts the feeding parameters according to the real-time weight signal fed back by the high-precision weighing sensor and the prediction result of the intelligent prediction model, so that the output of the electric actuator can precisely control the falling of each aggregate.

[0105] It can be understood that when traditional automated equipment processes coarse aggregates, due to the large single-particle mass and irregular shape of the aggregates, it is easy to cause the weighing error to exceed the allowable range. The present invention effectively solves the technical bottleneck in the weighing of coarse aggregates by the multi-stage feeding control strategy and the single-grain feeding mode, avoids the weighing error caused by the large single-particle mass of the coarse aggregates, improves the construction quality, reduces the project cost, and improves the construction efficiency, which has important practical application value for the construction of large-diameter pile foundations in karst areas.

[0106] Step S3: The PLC controller uses the integrated adaptive learning algorithm to dynamically adjust the feeding parameters according to the real-time data fed back by the high-precision weighing sensor and the integrated sensor system.

[0107] Figure 10 Schematic diagram of the data flow and optimization process of the adaptive learning algorithm provided by the present invention. Refer to Figure 10 , the adaptive learning algorithm specifically includes:

[0108] ① Data collection and preprocessing

[0109] Before the start of each feeding stage, the system tests the weight Wi, falling speed vi, and particle size distribution di of the current material through the high-precision weighing sensor and the integrated sensor system. These data provide the basis for subsequent analysis and optimization.

[0110] The collected data is normalized to eliminate the influence of different dimensions. The formula is:

[0111]

[0112] where μ and σ represent the mean and standard deviation respectively.

[0113] ② Feature extraction and model training

[0114] Extract the feature vector X = [W ′ , v ′ , d ′ , and these features reflect the key characteristics of the material during the weighing process. Among them, X is the feature vector, and W’, v’, and d’ are the normalized material weight, material falling speed, and particle size distribution respectively.

[0115] Use the neural network model for training. The neural network model structure corresponding to the adaptive learning algorithm is:

[0116] Input layer: 3 nodes (corresponding to the 3 features of the feature vector X).

[0117] Hidden layer: 3 layers, with 25 nodes in each layer, and the activation function is ReLU, which is used to extract complex features and patterns in the data;

[0118] Output layer: 2 nodes (corresponding to the feeding speed and the opening degree of the feeding port).

[0119] During the training process, the gradient descent method is used to optimize the parameters of the neural network model, and the loss function is the mean square error between the predicted feeding parameters of the model and the actual optimal feeding parameters:

[0120]

[0121] In the formula, v pred,iand k pred,i are the discharging speed and the opening degree of the discharging port at the i-th discharging stage predicted by the model, respectively, where v opt,i and k opt,i are the actual optimal discharging speed and the opening degree of the discharging port at the i-th discharging stage obtained through inverse calculation.

[0122] The neural network model parameters corresponding to the adaptive learning algorithm are updated using the backpropagation algorithm to optimize the prediction performance of the model. The specific update formula is as follows:

[0123]

[0124] where W and b represent the weights and biases of the model respectively, α is the learning rate, set to 0.01, and represent the partial derivatives of the loss function with respect to the weights and biases respectively, and the number of iterations is 1000 times.

[0125] The adaptive learning algorithm provided by the present invention can dynamically adjust the discharging speed and the opening degree of the discharging port according to the material characteristics and the real-time feedback during the weighing process by learning and optimizing the discharging parameters in real time. This helps to adapt to the optimal discharging strategy under different material conditions and improve the weighing accuracy and efficiency. For example, when dealing with materials with a higher density, the algorithm may reduce the discharging speed to prevent the weighing from exceeding the allowable range; while when dealing with materials with better fluidity, the discharging speed can be appropriately increased to improve the weighing efficiency.

[0126] The adaptive learning algorithm has strong adaptability and can cope with various complex working conditions, such as the characteristic changes of different batches of materials, the changes in environmental temperature and humidity, etc. Through continuous learning and optimization, the system can maintain high precision and high efficiency during long-term operation, reduce material waste and production delays caused by errors, and provide important technical support for fields such as building quality safety inspection.

[0127] In a preferred embodiment of the present invention, the method for weighing concrete raw materials provided by the present invention further includes:

[0128] The PLC controller uses the integrated intelligent prediction model to predict the falling speed and weight of the material in the next discharging stage according to the parameter characteristics of the material in the current discharging stage.

[0129] The intelligent prediction model adopts a multi-layer neural network structure, including an input layer, a hidden layer, and an output layer. Among them:

[0130] Input layer: Receives the feature vector X = [W ′ , v ′ , d ′ , and these feature vectors contain key information of the material during the weighing process, such as the normalized material weight, falling speed, and particle size distribution.

[0131] Hidden layer: A multi-layer neural network structure, each layer contains several nodes, and the activation function is ReLU, which is used to extract complex features and patterns in the data, providing a more accurate basis for prediction.

[0132] Output layer: Outputs the predicted falling speed v ppnd and weight W ppnd , providing a basis for subsequent adjustment of the discharging strategy.

[0133] The intelligent prediction model analyzes a large amount of historical weighing data and the corresponding variation laws of material parameters, and learns the falling speed and weight distribution characteristics of the material under different discharging parameters. This learning ability enables the model to predict the falling speed and weight of the current material according to the parameter characteristics of the material during the actual weighing process.

[0134] As a preferred implementation, before the start of each discharging stage, the intelligent prediction model can provide the prediction results to the adaptive learning algorithm. The adaptive learning algorithm optimizes the discharging parameters, such as the discharging speed and the opening degree of the discharging port, according to these prediction results to ensure the smooth falling of the material, improve the weighing accuracy, and realize the early adjustment of the discharging parameters.

[0135] The training process of the intelligent prediction model includes: The training process: The intelligent prediction model is trained using the historical weighing data set, and the cross-validation method is used to evaluate the model performance to ensure the generalization ability of the model on different data sets. The ratio of the training set to the validation set is 8:2. During the training process, regularization techniques (such as L1 regularization or L2 regularization) are used to prevent the model from overfitting and improve the generalization ability of the model.

[0136] The accuracy of the intelligent prediction model is verified by calculating the mean squared error (MSE) and the root mean squared error (RMSE) between the predicted value and the actual value. The prediction accuracy reaches ±0.1%, indicating that the model has a high prediction accuracy.

[0137] By predicting the falling speed and weight of the material in advance, the intelligent prediction model enables the system to adjust the discharging strategy in advance during the weighing process, reduce the weighing error, and improve the accuracy and stability of weighing. For example, during the weighing process, the system can dynamically adjust the opening degree and discharging speed of the discharging port according to the predicted material weight and falling speed to ensure that the material can accurately reach the target weight.

[0138] Based on the prediction results of the intelligent prediction model, the system can more accurately control the feeding process, reduce material waste and production delays caused by errors, and improve weighing efficiency and product quality. This prediction-based adjustment strategy enables the system to maintain high-precision weighing performance under different working conditions, providing important technical support for fields such as building quality safety inspection and ensuring the safety and reliability of construction projects.

[0139] Feedback Iteration and Continuous Optimization: After each weighing, by comparing the actual weighing result with the prediction result of the intelligent prediction model, calculate the error and feedback it into the intelligent prediction model for fine-tuning to achieve continuous optimization of the model. If there is a large deviation between the actual weighing weight and the target weight, it is necessary to adjust the model weights and biases according to the error to optimize the prediction performance of the model.

[0140] The calculation formula for the feedback error is:

[0141]

[0142] where E is the average error, W aaaaao,j is the actual weight of the j-th weighing, and W ppndpaand,j is the model-predicted material weight of the j-th weighing. N represents the total number of weighings.

[0143] Through the feedback iteration and continuous optimization mechanism, the accuracy and reliability of the intelligent prediction model during long-term operation are ensured.

[0144] The present invention provides a high-precision concrete raw material weighing system and method based on a multi-stage feeding control strategy. The system realizes precise weighing of concrete raw materials such as coarse aggregates by integrating an adaptive learning algorithm and an intelligent prediction model. During the design and implementation process, the system significantly improves weighing accuracy and response speed, strictly meeting the requirement of controlling the weighing quality error of aggregates within 0.5%. This method effectively solves the technical bottleneck in the weighing of coarse aggregates by traditional automation equipment, avoids weighing errors caused by the large single-particle mass of coarse aggregates, thereby improving building quality, reducing project costs, and increasing construction efficiency. For application scenarios such as the construction of large-diameter pile foundations in karst areas, this system has important practical application value.

[0145] The above-described embodiments merely represent several implementation manners of the present invention. Their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can still be made, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the appended claims.

[0146] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A concrete raw material weighing system based on a multi-level discharging control strategy, characterized in that, Comprising: A silo for storing materials, with a discharging opening provided at the bottom of the silo, and a material cylinder is arranged below the discharging opening to receive the discharged materials; A high-precision weighing sensor installed at the bottom of the material cylinder and connected to the PLC controller, for real-time monitoring of the material weight signal and transmitting it to the PLC controller; A PLC controller connected to the electric actuator, for generating control instructions according to the material weight signal and a preset multi-stage discharging control strategy; An electric actuator for receiving the control instructions of the PLC controller and adjusting the opening degree of the discharging opening to control the discharging speed.

2. The concrete raw material weighing system based on the multi-stage discharging control strategy according to claim 1, characterized in that The multi-stage discharging control strategy includes: Fast discharging stage: When the material weight obtained by the high-precision weighing sensor is less than the first weight threshold, the system continuously discharges materials at a preset discharging speed until the material weight reaches the first weight threshold; Medium-speed discharging stage: When the material weight is greater than or equal to the first weight threshold and less than the second weight threshold, the system automatically reduces the discharging speed and continues to discharge materials until the material weight reaches the second weight threshold; Slow discharging stage: When the material weight is greater than or equal to the second weight threshold and less than the third weight threshold, the system further reduces the discharging speed and slowly discharges materials until the material weight reaches the third weight threshold; Single-particle discharging stage: When the material weight is greater than or equal to the third weight threshold and less than the target weight, the system switches to the single-particle discharging mode to precisely control the falling of each aggregate until the material weight reaches the target weight.

3. The concrete raw material weighing system based on the multi-stage discharging control strategy according to claim 2, characterized in that Also comprising: An integrated sensor system connected to the PLC controller; the integrated sensor system includes a speed sensor and an image recognition sensor; The speed sensor is used for real-time monitoring of the material falling speed; The image recognition sensor is used for obtaining the particle size distribution, shape and volume of the materials.

4. The concrete raw material weighing system based on the multi-stage discharging control strategy according to claim 3, wherein, The PLC controller integrates an adaptive learning algorithm, for dynamically adjusting the discharging parameters according to the real-time data fed back by the high-precision weighing sensor and the integrated sensor system; wherein, the discharging parameters include the discharging speed and the opening degree of the discharging opening.

5. The concrete raw material weighing system based on the multi-stage discharging control strategy according to claim 4, wherein The PLC controller also integrates an intelligent prediction model, for predicting the material falling speed and weight in the next discharging stage according to the parameter characteristics of the materials in the current discharging stage, and providing a decision basis for the adaptive learning algorithm.

6. The method for weighing concrete raw materials of the concrete raw material weighing system based on the multi-stage discharging control strategy according to any one of claims 1-5, characterized in that, Comprising: After calibrating and setting parameters for the concrete raw material weighing system, start the system; The system adjusts the discharging speed in stages according to the real-time fed-back material weight signal and the preset multi-stage discharging control strategy; The PLC controller uses the integrated adaptive learning algorithm to dynamically adjust the discharging parameters according to the real-time data fed back by the high-precision weighing sensor and the integrated sensor system.

7. The concrete raw material weighing method according to claim 6, characterized in that, The method also includes: The PLC controller uses the integrated intelligent prediction model to predict the material falling speed and material weight in the next discharging stage according to the parameter characteristics of the materials in the current discharging stage.

8. The concrete raw material weighing method according to claim 6, wherein, The specific adaptive learning algorithm includes: Obtain the material weight collected by the high-precision weighing sensor, as well as the material falling speed and particle size distribution collected by the integrated sensor system; perform normalization processing on the obtained data; Based on the normalized data, extract the feature vector X = [W ′ , v ′ , d ′ ; where X is the feature vector, and W', v', and d' are the normalized material weight, material falling velocity, and particle size distribution, respectively; Training is performed using a neural network model; wherein, the input of the neural network model is the feature vector X, and the output is the discharging parameters predicted by the model; the discharging parameters include the discharging speed and the opening degree of the discharging port; During the training process, the gradient descent method is used to optimize the parameters of the neural network model, and the loss function is the mean square error between the discharging parameters predicted by the model and the actual optimal discharging parameters: where, v pred,i and k pred,i are respectively the discharging speed and the opening degree of the discharging port at the i-th discharging stage predicted by the model, v opt,i and k opt,i are the actual optimal discharging speed and the opening degree of the discharging port at the i-th discharging stage obtained through inverse calculation.

9. The concrete raw material weighing method according to claim 6, characterized in that The system adjusts the discharging speed in stages according to the real-time feedback of the material weight signal and the preset multi-stage discharging control strategy, including: Fast discharging stage: When the material weight obtained by the high-precision weighing sensor is less than the first weight threshold, the system discharges the material continuously at the preset discharging speed until the material weight reaches the first weight threshold; Medium-speed discharging stage: When the material weight is greater than or equal to the first weight threshold and less than the second weight threshold, the system automatically reduces the discharging speed and continues to discharge the material until the material weight reaches the second weight threshold; Slow discharging stage: When the material weight is greater than or equal to the second weight threshold and less than the third weight threshold, the system further reduces the discharging speed and discharges the material slowly until the material weight reaches the third weight threshold; Single-particle discharging stage: When the material weight is greater than or equal to the third weight threshold and less than the target weight, the system switches to the single-particle discharging mode to precisely control the falling of each aggregate until the material weight reaches the target weight.

10. The concrete raw material weighing method according to claim 9, characterized in that In the single-particle discharging stage, the PLC controller uses the integrated intelligent prediction model to predict the material falling speed and the material weight when the next material falls; The adaptive learning algorithm integrated in the PLC controller dynamically adjusts the discharging parameters according to the real-time weight signal feedback by the high-precision weighing sensor and the prediction result of the intelligent prediction model, so that the output of the electric actuator can precisely control the falling of each aggregate.

Images