Dual-mode belt conveyor adaptive control method, system, device, and storage medium

Abstract

The application relates to the technical field of automation control, and particularly provides a dual-mode belt conveying self-adaptive control method, a system, equipment and a storage medium, which comprises the following steps: receiving a mode selection instruction, determining a current control mode between an interval priority mode and a quantity priority mode; if the current control mode is the interval priority mode, determining the accommodable quantity of sand molds on a belt and final interval parameters through optimization calculation based on preset interval parameters and preset constraint conditions; if the current control mode is the quantity priority mode, determining the interval parameters of the sand molds on the belt and the final accommodable quantity through optimization calculation based on preset quantity parameters and preset constraint conditions; and generating control parameters for controlling the beat operation of the belt conveying system according to the optimization calculation result. The application provides two optional priority control modes, and combines parameter optimization and boundary protection mechanisms, so that the intelligent level and operation convenience of the belt conveying system control are significantly improved.

Description

Technical Field

[0001] This invention belongs to the field of adaptive control technology, specifically relating to a dual-mode belt conveyor adaptive control method, system, device, and storage medium. Background Technology

[0002] In the field of automated control of belt conveyor systems, traditional control methods often rely on operators manually calculating running time and interval parameters based on sand box specifications and setting them in a programmable logic controller (PLC). This manual setting method is not only cumbersome and time-consuming to debug, but also highly dependent on personnel experience, and prone to causing equipment collisions or blockages due to incorrect parameter settings. Especially in production scenarios where sand box specifications are frequently changed, repeated debugging seriously affects production efficiency and equipment flexibility. In addition, although some existing optimization solutions provide automatic calculation functions, they usually only support a single input mode and cannot flexibly adapt to differentiated production goals (such as maximizing capacity or minimizing cycle time). They also lack the ability to verify the safety boundaries of parameters and dynamically optimize belt space utilization, resulting in the need to improve the overall intelligence level and operational economy of the system. Summary of the Invention

[0003] In view of the above-mentioned shortcomings of the prior art, the present invention provides a dual-mode belt conveyor adaptive control method, system, device and storage medium to solve the above-mentioned technical problems.

[0004] In a first aspect, the present invention provides a dual-mode belt conveyor adaptive control method, comprising:

[0005] Receive mode selection instructions and determine the current control mode between interval priority mode and quantity priority mode;

[0006] If the current control mode is the interval priority mode, the number of sand molds that can be accommodated on the belt and the final interval parameters are determined by optimization calculation based on the preset interval parameters and preset constraints.

[0007] If the current control mode is quantity priority mode, the interval parameters and the final accommodating quantity of sand molds on the belt are determined by optimization calculation based on the preset quantity parameters and preset constraints.

[0008] Based on the results of the optimization calculations, control parameters are generated to control the cycle operation of the belt conveyor system.

[0009] In an optional implementation, receiving a mode selection instruction and determining the current control mode between an interval priority mode and a quantity priority mode includes:

[0010] Receive user selection instructions to determine the current control mode between interval priority mode and quantity priority mode.

[0011] In an optional implementation, receiving a mode selection instruction and determining the current control mode between an interval priority mode and a quantity priority mode includes:

[0012] Based on preset production targets or real-time monitored operating conditions, a mode selection instruction is generated to determine or switch to the corresponding interval priority mode or quantity priority mode.

[0013] The automatic determination of the control mode based on preset production targets includes: receiving a target instruction selected by the user from multiple preset production targets; mapping the selected production target instruction to a corresponding control mode instruction according to preset decision logic; the preset production targets include at least a target to maximize production capacity, a target to minimize cycle time, or a target to optimize energy consumption.

[0014] The control mode is automatically switched based on real-time monitored operating information, including: real-time monitoring of the congestion status downstream of the belt conveyor system; if congestion is detected downstream and the current operating mode is the quantity priority mode, the control mode is automatically switched to the interval priority mode, and an increased interval parameter is used to reduce the conveying rate.

[0015] In an optional implementation, based on preset interval parameters and preset constraints, the number of sand molds that can be accommodated on the conveyor belt and the final interval parameters are determined through optimization calculations, including:

[0016] The preset desired interval distance is compared with a preset minimum safe interval distance;

[0017] When the desired interval distance is less than the minimum safe interval distance, the minimum safe interval distance is used as the processed interval parameter;

[0018] Based on the total length of the belt, the length of the sand mold, and the interval parameters after processing, the theoretical number of sand molds is calculated.

[0019] The theoretical number of sand molds is rounded down to obtain the actual number of sand molds that can be accommodated.

[0020] Based on the total length of the belt, the length of the sand mold, and the actual number of sand molds that can be accommodated, the actual operating interval parameters are calculated.

[0021] In an optional implementation, based on preset quantity parameters and preset constraints, the spacing parameters and final accommodating quantity of sand molds on the conveyor belt are determined through optimization calculations, including:

[0022] Obtain the preset desired number of sand molds, and calculate the theoretical interval parameters based on the total belt length, sand mold length, and the desired number of sand molds;

[0023] The theoretical interval parameter is compared with a preset minimum safe interval distance;

[0024] When the theoretical interval parameter is less than the minimum safe interval distance, the minimum safe interval distance is used as the processed interval parameter;

[0025] Based on the total length of the belt, the length of the sand mold, and the processed interval parameters, the actual number of sand molds that can be accommodated is recalculated and rounded down.

[0026] Based on the total length of the belt, the length of the sand mold, and the actual number of sand molds that can be accommodated, the actual operating interval parameters are calculated.

[0027] In an optional implementation, based on the results of optimization calculations, control parameters for controlling the cycle time operation of the belt conveyor system are generated, including:

[0028] Obtain the belt speed;

[0029] Based on the actual operating interval parameters and the sand mold length, the belt running cycle time is calculated;

[0030] Control commands are generated based on the cycle time to control the periodic start and stop of the belt conveyor system.

[0031] In an optional implementation, it further includes:

[0032] Collect historical and real-time operational data, including at least sand mold physical property parameters, environmental parameters, and equipment operating status parameters;

[0033] The data is analyzed based on a machine learning model to dynamically optimize the preset minimum safety interval distance, thereby obtaining the dynamic minimum safety interval distance.

[0034] In the optimization calculation, the dynamic minimum safety interval distance is used to replace or supplement the original preset minimum safety interval distance.

[0035] Secondly, the present invention provides a dual-mode belt conveyor adaptive control system, comprising:

[0036] The mode selection module is used to receive mode selection instructions and determine the current control mode between interval priority mode and quantity priority mode;

[0037] The first control module is used to determine the number of sand molds that can be accommodated on the belt and the final interval parameters based on preset interval parameters and preset constraints if the current control mode is the interval priority mode.

[0038] The second control module is used to determine the spacing parameters and the final accommodating quantity of sand molds on the belt through optimization calculation based on preset quantity parameters and preset constraints if the current control mode is quantity priority mode.

[0039] The parameter generation module is used to generate control parameters for controlling the cycle operation of the belt conveyor system based on the results of optimization calculations.

[0040] Thirdly, a device is provided, comprising:

[0041] Memory for storing the dual-mode belt conveyor adaptive control program;

[0042] A processor is configured to implement the steps of the dual-mode belt conveyor adaptive control method as provided in the first aspect when executing the dual-mode belt conveyor adaptive control program.

[0043] Fourthly, a computer-readable storage medium is provided, on which a dual-mode belt conveyor adaptive control program is stored, wherein when the dual-mode belt conveyor adaptive control program is executed by a processor, the steps of the dual-mode belt conveyor adaptive control method provided in the first aspect are implemented.

[0044] The beneficial effects of this invention are as follows: the dual-mode belt conveyor adaptive control method, system, equipment, and storage medium provided by this invention significantly improve the intelligence level and ease of operation of the belt conveyor system control by offering two selectable priority control modes and integrating parameter optimization and boundary protection mechanisms. Its beneficial effects are mainly reflected in the following aspects: First, through dual-mode adaptive switching, the system can flexibly adapt to different production goals such as maximizing capacity and minimizing cycle time, enhancing production flexibility; Second, automatically completing core parameter calculations and safety verifications greatly reduces reliance on operator experience, reducing human error and debugging time; Third, the built-in optimization algorithm dynamically maximizes belt space utilization while ensuring safe intervals, improving conveying efficiency; Fourth, combining real-time data and machine learning capabilities, the system can achieve parameter self-optimization and status early warning, improving operational economy and equipment reliability. Attached Figure Description

[0045] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0046] Figure 1 This is a schematic flowchart of a method according to an embodiment of the present invention.

[0047] Figure 2This is another illustrative flowchart of a method according to an embodiment of the present invention.

[0048] Figure 3 This is a schematic block diagram of a system according to an embodiment of the present invention.

[0049] Figure 4 This is a schematic diagram of the structure of a device provided in an embodiment of the present invention. Detailed Implementation

[0050] To enable those skilled in the art to better understand the technical solutions of this invention, the technical solutions of the embodiments of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this invention, and not all embodiments. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this invention.

[0051] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention.

[0052] The dual-mode belt conveyor adaptive control method provided in this embodiment of the invention is executed by a computer device, and correspondingly, the dual-mode belt conveyor adaptive control system runs in the computer device.

[0053] Figure 1 This is a schematic flowchart illustrating a method according to an embodiment of the present invention. Wherein, Figure 1 The executing entity can be a dual-mode belt conveyor adaptive control system. Depending on different requirements, the order of steps in this flowchart can be changed, and some can be omitted.

[0054] like Figure 1 As shown, the method includes:

[0055] S1. Receive mode selection command and determine the current control mode between interval priority mode and quantity priority mode;

[0056] S2. If the current control mode is the interval priority mode, then based on the preset interval parameters and preset constraints, the number of sand molds that can be accommodated on the belt and the final interval parameters are determined by optimization calculation.

[0057] S3. If the current control mode is the quantity priority mode, then based on the preset quantity parameters and preset constraints, the interval parameters of the sand molds on the belt and the final accommodating quantity are determined by optimization calculation.

[0058] S4. Based on the results of the optimization calculation, generate control parameters for controlling the cycle operation of the belt conveyor system.

[0059] Please refer to Figure 2 The method flow of the present invention will be described in detail.

[0060] In one embodiment of the present invention, based on step S1, the following will provide a possible embodiment and describe its specific implementation in a non-limiting manner.

[0061] The first implementation method involves manual selection by the user. The operator directly selects "interval priority mode" or "quantity priority mode" through the human-machine interface, and the system enters the corresponding control process after receiving the instruction.

[0062] The second implementation method is intelligent system decision-making and adaptive switching, specifically including:

[0063] 1. Construction and Data Acquisition of the Perception Layer

[0064] The perception layer, as the foundation for the system to acquire internal and external state information, is implemented as follows:

[0065] Production target instruction reception: A "Production Target" selection area is set up on the human-machine interface, providing options such as "Maximize Capacity" and "Minimize Cycle Time". After the user selects, the advanced instruction is sent to the decision-making level.

[0066] Deployment of real-time operating condition monitoring network:

[0067] Downstream congestion monitoring: A set of photoelectric sensors is vertically installed at the downstream exit of the conveyor belt to form a light curtain. The system determines the congestion level (e.g., mild or severe) based on the number of sensors that are blocked.

[0068] Upstream material monitoring: A through-beam photoelectric sensor is installed on the inlet roller conveyor. The "upstream material shortage" or "insufficient material" is determined by monitoring whether the on / off frequency is consistently lower than the threshold.

[0069] Equipment status monitoring: Install current transformers on the drive motor to collect operating current data in real time to assess the health status of the load and equipment.

[0070] 2. Intelligent analysis and decision generation at the decision-making level

[0071] The decision-making layer includes a target decision-maker and a real-time rule engine, which together constitute the system's "intelligent brain".

[0072] The decision-making logic of the target decision-maker: It has an internally pre-set "target-mode-initial parameter" mapping table. For example, upon receiving the "maximize production capacity" instruction, it automatically triggers the "sand mold quantity mode" and operates at the minimum safety interval (S). minUsing ) as a constraint, the theoretical maximum quantity (N) is calculated. max ) as initial parameters.

[0073] Dynamic response of the real-time rules engine:

[0074] Congestion handling rules: When the light curtain determines "severe congestion" and the current mode is "quantity priority mode," the engine immediately generates a command to switch to "interval priority mode" and calculates an "emergency interval" (S) that is much larger than the normal value. emergency This is used as a new parameter to quickly reduce traffic. After the congestion is cleared, the system waits for a delay (e.g., 30 seconds) to confirm that the state is stable before automatically reverting to the efficient mode determined by the target decision-maker.

[0075] Material interruption handling rules: When the upstream sensor determines that the material is interrupted and the belt conveyor has finished conveying, the engine issues a "standby" command to control the motor to enter a low-speed inspection or pause state until the material supply resumes and it automatically restarts.

[0076] 3. Instruction execution and security integration at the execution layer

[0077] The execution layer is responsible for seamlessly translating intelligent decisions into equipment actions and integrating them with the existing control processes.

[0078] Parameter injection and process triggering: The mode instructions and optimization parameters (such as N) output by the decision-making layer max or S emergency The corresponding human-computer interface input box is automatically filled in, and the "start calculation" operation is simulated.

[0079] Inheritance and Verification: The system then enters the original "interval priority" or "quantity priority" calculation process, automatically inheriting and executing all existing boundary protections (such as verification S). 实 ≥S min The system incorporates round-down optimization and cycle time calculation logic to ensure that intelligent decisions are executed within a safe framework.

[0080] Control output: Finally, the belt motor is controlled to run according to the calculated cycle time (T), completing the closed loop from intelligent sensing and decision-making to precise execution.

[0081] In one embodiment of the present invention, based on step S2, the following will provide a possible embodiment and describe its specific implementation in a non-limiting manner.

[0082] First, the system receives the desired sand mold spacing distance (denoted as S) input by the user through the human-machine interface. Then, the system invokes a preset boundary protection algorithm to compare S with the minimum safe spacing distance pre-stored within the system (denoted as S0). min (This is a comparison.) minThese are fixed values ​​set according to the equipment's mechanical structure and safety specifications to prevent collisions between sand molds. If the comparison result is S... min The system will automatically adjust the temporary interval parameter ( Set as S min To ensure absolute safety; if S≥S min Then S 临 The value is directly taken as S.

[0083] Next, the system enters the spatial optimization calculation stage. It obtains the effective total length of the belt (L) and the length of the sand mold itself (D), according to the formula... Calculate the theoretical number of sand molds, N. Since the number of sand molds must be an integer, the system performs a floor operation on the calculated N value to obtain the actual integer number of sand molds that the conveyor belt can accommodate under the current constraints, denoted as Nactual. This floor operation is key to maximizing space utilization in this scheme.

[0084] Finally, in order to obtain accurate operating parameters, the system is based on the final N. 实 Perform the reverse calculation. Use the formula. Calculate the specific interval distance S used in actual operation. 实 At this point, the system has determined a set of optimal operating parameters for this mode: the actual number of sand molds N. 实 and actual interval distance S 实 Subsequently, the system will be based on S 实 Based on the values ​​of D and belt speed V, the cycle time T is calculated, and the periodic operation of the belt conveyor system is controlled accordingly.

[0085] In one embodiment of the present invention, based on step S3, the following will provide a possible embodiment and describe its specific implementation in a non-limiting manner.

[0086] In the quantity-first mode, the core task of the system is to optimize and determine the actual interval parameters and the final number of sand molds that can be accommodated during belt operation, based on the user-defined desired number of sand molds, while ensuring safety and a reasonable layout. The specific implementation steps of this mode are as follows:

[0087] First, the system receives the desired number of sand molds (denoted as N) input by the user through the human-machine interface. Then, based on the effective total length of the conveyor belt (L) and the length of the sand mold (D), the system calculates a theoretical sand mold spacing distance S according to the formula S=L / ND. This calculation aims to preliminarily assess the required spacing under uniform distribution and quantity requirements.

[0088] Next, the system initiates a security check. It compares the calculated theoretical interval S with the preset minimum safe interval distance (S0). min ) for comparison. If S min ​​This indicates that directly laying out the desired quantity will result in too small an interval and a risk of collision. Therefore, the system will forcibly adjust the temporary interval parameter (S). 临 Set as S min To ensure basic safety; if S≥S min If S is a critical value, then S is a critical value.

[0089] Then, the system enters the optimization and adjustment phase. This is because the interval parameter may be adjusted to S due to security checks. min The originally expected quantity N may not be achievable under safety constraints. Therefore, the system needs to be based on a determined S. 临 Re-apply to the formula N'=L / (S) 临 +D) Calculate the theoretical number of sand molds N'. Similarly, round down N' to obtain the maximum integer number of sand molds that the conveyor belt can actually accommodate under the safety interval constraint, denoted as N. 实 .

[0090] Finally, to obtain accurate and executable operating parameters, the system performs parameter inverse calculation. This is done using the finally determined N. 实 According to formula S 实 =L / N 实 -D calculates the specific interval distance S used in actual operation. 实 At this point, the system outputs a set of optimized operating parameters: the actual number of sand molds that can be accommodated, N. 实 and actual interval distance S 实 Subsequently, the system will be based on S 实 The cycle time T is calculated based on D and belt speed V, and the belt operation is controlled accordingly.

[0091] In one embodiment of the present invention, based on step S4, the following will provide a possible embodiment and describe its specific implementation in a non-limiting manner.

[0092] The parameter optimization calculation is completed using either of the aforementioned modes (interval priority or quantity priority), and the actual operating interval parameter (S) is determined. 实 ) and the actual number of sand molds that can be accommodated (N) 实 After that, generate specific beat control instructions by following these steps:

[0093] Step 1: Obtain the running baseline parameters

[0094] The constant operating speed of the belt conveyor is obtained from a preset configuration database or through field sensors, denoted as V (the unit is usually meters per second or meters per minute). This speed V is a key parameter for calculating the time base.

[0095] Step 2: Calculate the cycle time for a single conveyor.

[0096] Based on the determined actual interval parameter S实 Given the sand mold length D, calculate the time required for a single "sand mold and its subsequent interval" to pass through a fixed point as a complete conveying unit, i.e., the cycle time T. The calculation formula is:

[0097]

[0098] The physical meaning of this formula is: to transport a complete unit (of length S) 实 +D) The required duration. This cycle time T is the direct time basis for the control system to periodically start and stop the belt or adjust its speed.

[0099] Step 3: Generate and execute periodic control instructions

[0100] The core controller (such as a PLC or industrial PC) generates corresponding timing control instructions based on the calculated cycle time T. A typical control logic is as follows: the controller drives the belt motor to start, runs for a duration T, then stops, waiting for the next sand mold to be in place or for other process conditions to be met before restarting for the next duration T, and so on. This periodic control of "run-stop-wait-restart" ensures that each sand mold runs according to the calculated optimal interval S. 实 It is precisely and rhythmically conveyed forward on the belt.

[0101] Based on the above embodiments, in order to further improve the reliability of automatic control, in one embodiment, the minimum safe distance is optimized, and the optimization method includes:

[0102] As an enhancement module for the core dual-mode adaptive control method, its design goal is to overcome the limitations of traditional control systems where parameters rely on manual experience and remain static for a long time. By introducing real-time data perception, machine learning analysis, and dynamic parameter adjustment, it constructs an intelligent closed loop with "perception-learning-optimization" capabilities. This transforms the key safety parameter of minimum safe interval distance from a fixed value to an optimized value that is dynamically adjusted according to operating conditions, thereby continuously approaching the limits of equipment operating efficiency while absolutely ensuring safety.

[0103] The system adopts a layered architecture, primarily comprising a data acquisition and processing layer, an intelligent analysis and decision-making layer, and a control execution and integration layer. These three layers interact through standardized data interfaces and communication protocols, ensuring the system is modular, scalable, and easy to maintain.

[0104] 1. Detailed implementation method of the data acquisition and processing layer:

[0105] Data is the cornerstone of intelligent optimization. This layer is responsible for collecting and transmitting various types of data related to the process comprehensively and with high precision, and for preprocessing them to provide high-quality data raw materials for upper-level analysis.

[0106] (1) Expanding the deployment of sensor networks:

[0107] Sand mold physical property parameter acquisition:

[0108] Weight: A high-precision dynamic weighing module is integrated at the sand mold loading station or conveyor line entrance. The system automatically records the weight (W) of each sand mold as it passes through, with data accuracy typically required to be within ±0.5%. Weight is a key factor affecting inertia, stopping accuracy, and drive load.

[0109] Surface condition / dimension: Install an industrial vision inspection system (such as a line scan camera or 3D scanner) at the online workstation. Through image processing algorithms, the surface roughness of the sand mold can be indirectly evaluated (qualitatively classified, such as smooth, normal, rough), and the length (D) and width of the sand mold can be verified to ensure consistency with preset parameters, and abnormal sand molds can be excluded from the system.

[0110] Environmental parameter collection:

[0111] Temperature and humidity: Install temperature and humidity sensors at key locations along the belt conveyor (especially the drive section and the load-bearing section) to monitor the ambient temperature (T) in real time. env ) and relative humidity (H env Changes in temperature and humidity can affect the coefficient of friction of the belt material, its tension, and the heat dissipation efficiency of the drive motor.

[0112] Equipment operating status parameter acquisition:

[0113] Motor drive current: Three-phase current waveform data is acquired at high frequency from the inverter output of the drive motor or directly using a clamp-on current sensor. This process includes obtaining the effective value of the current (I0). rms In addition to reflecting the average load, it is more important to analyze the harmonic components of the current, whose changes can provide early warnings of mechanical misalignment, bearing wear, or sudden load changes.

[0114] Vibration data: Triaxial vibration acceleration sensors are installed on key rotating components such as the drive motor bearing housing and the drive wheel bearing housing. The sampling frequency needs to be high enough (usually ≥1 kHz) to capture fault characteristic frequencies such as bearing damage and abnormal gear meshing.

[0115] Belt speed and position: A high-precision encoder mounted on the driven pulley provides real-time feedback on the actual belt speed (V). actual (and position information, used to calibrate control commands and calculate actual beats.)

[0116] (2) Construction and preprocessing of the data platform:

[0117] Unified Data Platform: An industrial IoT platform or time-series database (such as InfluxDB, TDengine) is used as the data hub. All sensor data, control parameters (mode of each run, input S or N, calculated T, etc.), and production task identifiers (sand mold product code, batch number) are accurately timestamped and then streamed into the platform.

[0118] Data association and rich context: Through the production management system (MES) interface or RFID scanning, each delivery task is associated with specific sand mold product specifications and process requirements, giving the data a production context.

[0119] Data preprocessing pipeline:

[0120] Cleaning: Automatically identifies and removes abnormal values ​​(such as flying points) caused by momentary sensor failures or communication interference.

[0121] Alignment: Since different sensors have different sampling frequencies, the system uses the control cycle or a fixed time window (such as 100ms) as a reference to synchronize and align all data in time.

[0122] Preliminary feature extraction: Online calculation of some statistical features, such as the mean and variance of the weight of each batch of sand molds, the fluctuation range of the current in the most recent minute, and the root mean square value (RMS) of the vibration acceleration.

[0123] Storage: The processed data is stored in two parts: a real-time cache to support online model inference; and a historical repository for offline model training and long-term trend analysis.

[0124] 2. Implementation methods of the intelligent analysis and decision-making layer:

[0125] (1) Construction and training of machine learning models (offline stage):

[0126] Optimization objective definition: The ultimate goal of the model is to maximize the space utilization of the conveyor belt while ensuring zero collisions and zero slippage under any operating conditions. This directly translates to finding a contextualized, as small as possible yet still safe, dynamic minimum safety clearance distance (S). min,dynamic ).

[0127] Feature engineering:

[0128] Static characteristics: Sand mold product code (containing material and process information), preset sand mold length (D), preset sand mold weight (W) nominal ).

[0129] Dynamic operating condition characteristics: The measured weight (W) of the current sand mold. actual ), surface roughness category, ambient temperature (T) env ), ambient humidity (H)env ), belt preset speed (V) set ).

[0130] Historical operating characteristics: Statistical values ​​(such as median, minimum) of the successful operating intervals of the same or similar sand molds under similar environments over a past period (such as 1 hour).

[0131] Label definition and sample construction:

[0132] Positive Samples (Learnable Safety Intervals): Filter all "successful and stable" operation records from historical data. "Successful and stable" means that the operation did not trigger any collision, emergency stop, or slippage alarms, and that equipment vibration and current were within normal ranges. The actual safety interval distance used in the record (i.e., S after boundary protection processing) 临 This is considered an "acceptable safety value" under that specific operating condition. In particular, those records that successfully operated using smaller intervals represent the "better, more compact" safety boundaries that we hope the model will learn.

[0133] Negative samples (safety boundary): Collect all historical records that triggered equipment alarms or operational instability. Analyze the operating parameters and set intervals before these records occurred; these data points collectively define the safe "no-go zones".

[0134] Model selection and training:

[0135] This approach recommends using Gaussian process regression (GPR) or a Bayesian optimization model based on safety constraints. These models can provide not only predicted values ​​(S...) min,dynamic It can also provide the range of uncertainty in the prediction, which is crucial for safety-critical applications.

[0136] Training process: Historical feature data is used as input (X), and the corresponding "safety interval distance" (positive sample) or "hazard marker" (negative sample) is used as the target (Y). The model will learn a complex mapping function f(X)→S from multi-dimensional working condition features to safety interval distance. min,dynamic .

[0137] Safety constraint injection: During training or inference, the model must strictly adhere to the "hard constraints" learned from negative samples to ensure its recommended S min,dynamic Always stay above the known danger boundary, with a certain safety margin (which can be adjusted via hyperparameters).

[0138] (2) Dynamic optimization reasoning (online phase):

[0139] When the operator is ready to start a new conveying task and sets the sand mold parameters, the control system will first trigger the intelligent optimization module before entering the standard dual-mode calculation process.

[0140] Real-time feature assembly: The system obtains real-time and near-historical feature data of the current task from the data platform and assembles them into feature vectors that meet the input requirements of the model.

[0141] Model Invocation and Inference: The feature vector is input into the deployed machine learning model. The model returns two core outputs within milliseconds: 1) the recommended dynamic minimum safe margin distance (S min,dynamic ); 2) The confidence level or uncertainty of the recommended value.

[0142] Decision-making and output:

[0143] If the confidence level is higher than the preset threshold (e.g., 95%), the system adopts S. min,dynamic .

[0144] If the confidence level is insufficient (e.g., encountering a completely new combination of operating conditions that the model has not learned before), the system automatically reverts to using a globally preset, conservative fixed S. min This "unknown working condition" is recorded and prompted for review by engineers. This new data can then be added to the training set to expand the model's capabilities.

[0145] Ultimately, the "minimum safe interval distance" to be used in this operation was determined.

[0146] 3. Seamless integration of the control execution layer

[0147] (1) Parameter injection mechanism:

[0148] In both "interval priority mode" and "quantity priority mode", the benchmark value used for boundary comparison is no longer a fixed "preset minimum safety interval distance (S)". min Instead of replacing ")," it is replaced with "minimum safe interval distance" output from the previous step.

[0149] This replacement is transparent to the upper-level control logic. The original comparison logic (if S...) remains unchanged. input min , then S 临 = S min The comparison threshold remains completely unchanged, only the comparison threshold becomes more intelligent and adaptive.

[0150] (2) Closed-loop optimization and continuous learning:

[0151] Performance feedback: After each run, the actual operating conditions and the S used in this run are recorded. min,dynamic ​The values ​​and the final running results (success / stable / alarm) will all be returned to the data platform as new data points.

[0152] Model Iteration Updates: The system periodically (e.g., weekly) or after accumulating sufficient new data, initiates a background model retraining process. The model is incrementally trained or fully retrained using a dataset containing the new data, enabling it to adapt to changes in production conditions (such as slow equipment wear and tear, seasonal changes) and achieve continuous capability evolution.

[0153] Safety Monitoring: An independent safety monitoring module continuously compares the model's recommended values ​​with the actual operational safety margin. If the model's recommended values ​​are found to be too aggressive over a period of time, causing the frequency of safety alarms to approach the threshold, the system will automatically trigger an alarm and may temporarily switch back to a more conservative fixed-parameter mode, requiring engineer intervention for investigation.

[0154] 4. System Deployment and Benefit Summary

[0155] Through the above specific implementation, the data-driven intelligent optimization system successfully upgraded static control to dynamic self-optimizing control. Its core benefits are reflected in:

[0156] Enhanced security: Boundaries learned from real historical data better reflect the actual security limits of a device than fixed boundaries estimated purely theoretically.

[0157] Maximizing efficiency: By contextually compressing unnecessary safety margins and maximizing conveyor density or shortening intervals within safe limits, belt utilization and overall capacity are directly improved.

[0158] Highly adaptable: The system can automatically adapt to changes in sand mold characteristics, environmental fluctuations, and slow changes in equipment status, reducing the frequency of manual parameter adjustments.

[0159] It has predictive potential: the collected equipment status data (current, vibration) can be used to train independent predictive maintenance models to achieve early warning of faults.

[0160] In some embodiments, the dual-mode belt conveyor adaptive control system may include multiple functional modules composed of computer program segments. The computer programs for each program segment in the dual-mode belt conveyor adaptive control system may be stored in the memory of a computer device and executed by at least one processor to perform (see details). Figure 1 (Description) The function of adaptive control for dual-mode belt conveyor.

[0161] In this embodiment, the dual-mode belt conveyor adaptive control system can be divided into multiple functional modules according to its functions, such as... Figure 3As shown. The module referred to in this invention is a series of computer program segments that can be executed by at least one processor and perform a fixed function, and is stored in memory. In this embodiment, the functions of each module will be described in detail in subsequent embodiments.

[0162] The mode selection module is used to receive mode selection instructions and determine the current control mode between interval priority mode and quantity priority mode;

[0163] The first control module is used to determine the number of sand molds that can be accommodated on the belt and the final interval parameters based on preset interval parameters and preset constraints if the current control mode is the interval priority mode.

[0164] The second control module is used to determine the spacing parameters and the final accommodating quantity of sand molds on the belt through optimization calculation based on preset quantity parameters and preset constraints if the current control mode is quantity priority mode.

[0165] The parameter generation module is used to generate control parameters for controlling the cycle operation of the belt conveyor system based on the results of optimization calculations.

[0166] Figure 4 The dual-mode belt conveyor adaptive control method provided in the embodiments of this application can be applied to equipment. Those skilled in the art will understand that the equipment structure involved in the embodiments of this invention does not constitute a limitation on the equipment. The equipment may include more or fewer components than illustrated, or combine certain components, or have different component arrangements. In the embodiments of this invention, the equipment includes, but is not limited to, laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The equipment may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the embodiments of this application described and / or claimed herein.

[0167] The device 400 may include a processor 410, a memory 420, and a communication unit 430. These components communicate via one or more buses. Those skilled in the art will understand that the server structure shown in the figure does not constitute a limitation of the present invention. It may be a bus topology or a star topology, and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0168] The memory 420 can be used to store execution instructions of the processor 410. The memory 420 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. When the execution instructions in the memory 420 are executed by the processor 410, the device 400 is able to perform some or all of the steps in the above method embodiments.

[0169] The processor 410 serves as the control center of the storage device, connecting various parts of the electronic device via various interfaces and lines. It executes software programs and / or modules stored in the memory 420, and calls data stored in the memory to perform various functions of the electronic device and / or process data. The processor can be composed of integrated circuits (ICs), such as a single packaged IC or multiple packaged ICs with the same or different functions connected together. For example, the processor 410 may consist only of a central processing unit (CPU). In this embodiment of the invention, the CPU may have a single processing core or include multiple processing cores.

[0170] The communication unit 430 is used to establish a communication channel, enabling the storage device to communicate with other devices. It can receive user data sent by other devices or send user data to other devices.

[0171] The present invention also provides a computer storage medium, wherein the computer storage medium may store a program, which, when executed, may include some or all of the steps provided in the embodiments of the present invention. The storage medium may be a magnetic disk, an optical disk, read-only memory (ROM), or random access memory (RAM), etc.

[0172] Those skilled in the art will clearly understand that the techniques in the embodiments of the present invention can be implemented using software plus necessary general-purpose hardware platforms. Based on this understanding, the technical solutions in the embodiments of the present invention, or the parts that contribute to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium such as a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, or any other medium capable of storing program code. It includes several instructions to cause a computer device (which may be a personal computer, a server, or a second device, network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention.

[0173] The same or similar parts between the various embodiments in this specification can be referred to mutually. In particular, the device embodiments are basically similar to the method embodiments, so the description is relatively simple, and the relevant parts can be referred to the description in the method embodiments.

[0174] In the embodiments provided by this invention, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative. For instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between systems or modules may be electrical, mechanical, or other forms.

[0175] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical modules; that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0176] In addition, the functional modules in the various embodiments of the present invention can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module.

[0177] Although the present invention has been described in detail with reference to the accompanying drawings and preferred embodiments, the present invention is not limited thereto. Various equivalent modifications or substitutions can be made to the embodiments of the present invention by those skilled in the art without departing from the spirit and essence of the invention, and such modifications or substitutions should all be within the scope of the present invention. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should also be covered within the protection scope of the present invention.

Claims

1. An adaptive control method for dual-mode belt conveyor, characterized in that, include: Receive mode selection instructions and determine the current control mode between interval priority mode and quantity priority mode; If the current control mode is the interval priority mode, the number of sand molds that can be accommodated on the belt and the final interval parameters are determined by optimization calculation based on the preset interval parameters and preset constraints. If the current control mode is quantity priority mode, the interval parameters and the final accommodating quantity of sand molds on the belt are determined by optimization calculation based on the preset quantity parameters and preset constraints. Based on the results of the optimization calculations, control parameters are generated to control the cycle operation of the belt conveyor system. Based on preset interval parameters and preset constraints, the maximum number of sand molds that can be accommodated on the conveyor belt and the final interval parameters are determined through optimization calculations, including: The preset desired interval distance is compared with a preset minimum safe interval distance; When the expected interval distance is less than the minimum safe interval distance, the minimum safe interval distance is used as the processed interval parameter; when the expected interval distance is not less than the minimum safe interval distance, the expected interval distance is used as the processed interval parameter. Based on the total length of the belt, the length of the sand mold, and the interval parameters after processing, the theoretical number of sand molds is calculated. The theoretical number of sand molds is rounded down to obtain the actual number of sand molds that can be accommodated. Based on the total length of the belt, the length of the sand mold, and the actual number of sand molds that can be accommodated, the actual operating interval parameters are calculated. Based on preset quantity parameters and preset constraints, the spacing parameters and final accommodating quantity of sand molds on the conveyor belt are determined through optimization calculations, including: Obtain the preset desired number of sand molds, and calculate the theoretical interval parameters based on the total belt length, sand mold length, and the desired number of sand molds; The theoretical interval parameter is compared with a preset minimum safe interval distance; When the theoretical interval parameter is less than the minimum safe interval distance, the minimum safe interval distance is used as the processed interval parameter; Based on the total length of the belt, the length of the sand mold, and the processed interval parameters, the actual number of sand molds that can be accommodated is recalculated and rounded down. Based on the total length of the belt, the length of the sand mold, and the actual number of sand molds that can be accommodated, the actual operating interval parameters are calculated.

2. The method according to claim 1, characterized in that, The receive mode selection command determines the current control mode between interval priority mode and quantity priority mode, including: Receive user selection instructions to determine the current control mode between interval priority mode and quantity priority mode.

3. The method according to claim 1, characterized in that, The receive mode selection command determines the current control mode between interval priority mode and quantity priority mode, including: Based on preset production targets or real-time monitored operating conditions, a mode selection instruction is generated to determine or switch to the corresponding interval priority mode or quantity priority mode. The automatic determination of the control mode based on preset production targets includes: receiving a target instruction selected by the user from multiple preset production targets; mapping the selected production target instruction to a corresponding control mode instruction according to preset decision logic; the preset production targets include at least a target to maximize production capacity, a target to minimize cycle time, or a target to optimize energy consumption. The control mode is automatically switched based on real-time monitored operating information, including: real-time monitoring of the congestion status downstream of the belt conveyor system; if congestion is detected downstream and the current operating mode is the quantity priority mode, the control mode is automatically switched to the interval priority mode, and an increased interval parameter is used to reduce the conveying rate.

4. The method according to claim 1, characterized in that, Based on the results of the optimization calculations, control parameters for controlling the cycle time operation of the belt conveyor system are generated, including: Obtain the belt speed; Based on the actual operating interval parameters and sand mold length, calculate the belt running cycle time; Control commands are generated based on the cycle time to control the periodic start and stop of the belt conveyor system.

5. The method according to claim 1, characterized in that, The method further includes: Collect historical and real-time operational data, including at least sand mold physical property parameters, environmental parameters, and equipment operating status parameters; The data is analyzed based on a machine learning model to dynamically optimize the preset minimum safety interval distance, thereby obtaining the dynamic minimum safety interval distance. In the optimization calculation, the dynamic minimum safety interval distance is used to replace or supplement the original preset minimum safety interval distance.

6. A dual-mode belt conveyor adaptive control system, used to execute the dual-mode belt conveyor adaptive control method according to any one of claims 1-5, characterized in that, include: The mode selection module is used to receive mode selection instructions and determine the current control mode between interval priority mode and quantity priority mode; The first control module is used to determine the number of sand molds that can be accommodated on the belt and the final interval parameters based on preset interval parameters and preset constraints if the current control mode is the interval priority mode. The second control module is used to determine the spacing parameters and the final accommodating quantity of sand molds on the belt through optimization calculation based on preset quantity parameters and preset constraints if the current control mode is quantity priority mode. The parameter generation module is used to generate control parameters for controlling the cycle operation of the belt conveyor system based on the results of optimization calculations.

7. A dual-mode belt conveyor adaptive control device, characterized in that, include: Memory for storing the dual-mode belt conveyor adaptive control program; A processor is configured to implement the steps of the dual-mode belt conveyor adaptive control method as described in any one of claims 1-5 when executing the dual-mode belt conveyor adaptive control program.

8. A computer-readable storage medium storing a computer program, characterized in that, The readable storage medium stores a dual-mode belt conveyor adaptive control program, which, when executed by a processor, implements the steps of the dual-mode belt conveyor adaptive control method as described in any one of claims 1-5.

Images