Boric acid production material scheduling method and system based on Internet of Things

Abstract

The invention discloses a boric acid production material scheduling method and system based on the Internet of Things, and the method comprises the steps: obtaining multi-source data from a boric acid production line, carrying out the preprocessing of the multi-source data, and mapping the preprocessed multi-source data to a digital twinborn model; and extracting the scheduling demand of the current workshop from the initial parameters of the digital twin model and the preprocessed multi-source data vector, and constructing a multi-target scheduling model when the scheduling demand meets the workshop production demand. The turbidity, crystal particle characteristics and color change of a solution on a production line are monitored in real time through an optical system, optical monitoring data are obtained, the crystallization state and the impurity content in the solution are determined in combination with multi-source data, and scheduling execution is carried out when the crystallization state or the impurity content deviates from a normal range. The optical monitoring data and the scheduling execution condition are fed back to the digital twinborn model based on the abnormal indication, so that the scheduling strategy and the process parameters of the boric acid production line are corrected, and the intelligence and the production efficiency of boric acid production are improved.

Description

Technical Field

[0001] The present invention belongs to the technical fields of the Internet of Things and production scheduling control, and more specifically, relates to a boric acid production material scheduling method and system based on the Internet of Things. Background Technique

[0002] Material scheduling is an important technology in the fields of modern manufacturing and logistics, which involves the management and optimization of aspects such as material requirements, inventory, transportation, and distribution. With the expansion of production scale and the intensification of market competition, the importance of material scheduling has become increasingly prominent.

[0003] Currently, the material scheduling on the boric acid production line still relies heavily on manual labor. Moreover, in the traditional boric acid production line, single instruments are mostly used for data measurement, and the data coverage of single instruments is relatively insufficient, and the acquisition period is also long, resulting in low material scheduling efficiency and being prone to errors. In addition, due to the particularity of boric acid production, its requirements for the environment are often relatively harsh. For example, parameters such as the temperature, flow rate in the reaction kettle, and the turbidity and crystallization of the internal liquid have important influence significance on its production. In the prior art, the state of the internal liquid in boric acid production is often ignored, and ignoring the state of the reaction liquid may lead to production according to the original feeding and scheduling methods under abnormal conditions, which to a certain extent affects the output and production quality of boric acid. Summary of the Invention

[0004] To solve the deficiencies in the prior art, the purpose of the present invention is to solve the above-mentioned defects, and further propose a boric acid production material scheduling method and system based on the Internet of Things.

[0005] The present invention adopts the following technical solutions.

[0006] The first aspect of the present invention discloses a boric acid production material scheduling method based on the Internet of Things, and the method includes:

[0007] Obtain multi-source data from the boric acid production line, and preprocess the multi-source data to map the preprocessed multi-source data to a digital twin model;

[0008] Extract the scheduling requirements of the current workshop from the initial parameters of the digital twin model and the preprocessed multi-source data vector, and construct a multi-objective scheduling model when the scheduling requirements meet the workshop production requirements;

[0009] Real-time monitor the turbidity, crystal particle characteristics, and color change of the solution on the production line through an optical system to obtain optical monitoring data, and determine the internal crystal state and impurity content of the solution in combination with the multi-source data, so as to perform scheduling execution when the crystal state or impurity content deviates from the normal range;

[0010] Based on the anomaly indication, the optical monitoring data and the scheduling execution status are fed back to the digital twin model to correct the scheduling strategy and process parameters of the boric acid production line;

[0011] Among them, the multi-source data includes sensor data of temperature, flow rate, pH, and pressure installed at multiple key nodes on the boric acid production line. The preprocessing includes missing value filling and denoising filtering. The multi-objective scheduling model is used to output scheduling decisions according to scheduling requirements and resource lists.

[0012] Furthermore, the obtaining of multi-source data from the boric acid production line and the preprocessing of the multi-source data to map the preprocessed multi-source data to the digital twin model includes:

[0013] Generating an original data vector based on the instantaneous readings of different sensors from the boric acid production line, and performing missing value filling and denoising filtering on the original data vector to obtain a preprocessed data vector;

[0014] Determining key process variables based on the preprocessed data vector, and mapping the key process variables into the digital twin structure to build the digital twin model, obtaining an initial parameter vector of the digital twin model;

[0015] Among them, the key process variables include temperature, boron ore impurity content, and flow rate, and the initial parameter vector includes the initial modeling values of the reaction temperature, flow rate, and pH of the boric acid production line.

[0016] Furthermore, the obtaining of multi-source data from the boric acid production line and the preprocessing of the multi-source data to map the preprocessed multi-source data to the digital twin model further includes:

[0017] Comparing the established digital twin model with the actual monitoring data to obtain the error between the model output and the actual monitoring data, and determining whether the error exceeds a first threshold;

[0018] When the error exceeds the first threshold, the initial parameters of the digital twin model are preprocessed again or the bias of the sensor is corrected to obtain the verification result of the digital twin model and the corrected model parameters.

[0019] Furthermore, extracting the scheduling requirements of the current workshop from the initial parameters of the digital twin model and the preprocessed multi-source data vector, and constructing a multi-objective scheduling model when the scheduling requirements meet the production requirements of the workshop, includes:

[0020] Determine the key parameters of the total feeding amount, feeding frequency, and expected output based on the inventory data, flow rate, temperature, and pH of the boric acid production line in the digital twin model, and summarize and generate a scheduling demand vector in combination with the workshop equipment capacity and personnel configuration;

[0021] Set a multi-objective function for defining the decision variable vector, and obtain the scheduling decision variable vector based on the multi-objective function to construct the multi-objective scheduling model;

[0022] Among them, the multi-objective function includes minimizing the total transportation time, minimizing the energy consumption, and maximizing the production capacity utilization rate, and the variable vector for decision-making includes all batch feeding times or the route selection of transportation vehicles within the scheduling decision number.

[0023] Further, extracting the scheduling requirements of the current workshop from the initial parameters of the digital twin model and the preprocessed multi-source data vector, and when the scheduling requirements meet the workshop production requirements, constructing a multi-objective scheduling model further includes:

[0024] When the optical sensor monitors that the turbidity of the solution or the size of the crystal particles is abnormal, trigger and transmit a first feedback signal through the data interaction interface between the multi-objective scheduling model and the optical system, and when the multi-objective scheduling model captures the first feedback signal, fine-tune the corresponding feeding time or batch sequence;

[0025] When the crystallization rate of the current feeding batch exceeds the second threshold, trigger and transmit a second feedback signal, and when the multi-objective scheduling model captures the second feedback signal, delay the subsequent material conveying time or reduce the single feeding amount;

[0026] Construct an adaptive function based on the first feedback signal and the second feedback signal, and obtain a revised scheduling decision based on the adaptive function on the basis of the original adjustment strategy, and the revised scheduling decision is used to generate a scheduling execution instruction.

[0027] Further, the optical system is used to monitor the turbidity, crystal particle characteristics, and color change of the solution on the production line in real time, obtain optical monitoring data, and determine the internal crystal state and impurity content of the solution in combination with the multi-source data, so as to perform scheduling execution when the crystal state or impurity content deviates from the normal range, including:

[0028] Monitor the turbidity, crystal particle characteristics, and color change of the solution in real time according to the set sampling frequency through the optical sensor installed at the outlet of the reactor or the entrance of the crystallization workshop, obtain the optical data vector, and fuse the optical data vector with the multi-source data to construct a fusion vector;

[0029] Call abnormal detection on the fusion vector based on the set normal working range threshold or machine learning algorithm, and when the fusion vector is abnormal, trigger the control system to give an early warning and automatic adjustment to generate an abnormal index quantity;

[0030] Obtain the defined control strategy function based on the abnormal index quantity and the correction quantity of the original adjustment strategy, and when the abnormal index quantity is the first value, revise the production scheduling variables through the digital twin model to obtain a revised scheduling plan.

[0031] Further, feedback the optical monitoring data and the scheduling execution situation to the digital twin model based on the abnormal indication to correct the scheduling strategy and process parameters of the boric acid production line, including:

[0032] Obtain the execution instruction and the execution data log based on the revised scheduling plan, and combine the abnormal record and the optical monitoring data to construct a historical data matrix, so as to use a machine learning model to predict the crystallization state or energy consumption at different times based on the historical data matrix;

[0033] Optimize the scheduling strategy and the optical threshold based on the prediction result of the machine learning model to construct an optimization objective function, obtain the updated new model parameters, and map the new model parameters to the digital twin model.

[0034] The second aspect of the present invention discloses an Internet of Things-based boric acid production material scheduling system, and the system includes:

[0035] A data preprocessing module for obtaining multi-source data from the boric acid production line and preprocessing the multi-source data to map the preprocessed multi-source data to the digital twin model;

[0036] A model construction module for extracting the scheduling requirements of the current workshop from the initial parameters of the digital twin model and the preprocessed multi-source data vector, and constructing a multi-objective scheduling model when the scheduling requirements meet the workshop production requirements;

[0037] A scheduling execution module for real-time monitoring of the turbidity, crystal particle characteristics and color change of the solution on the production line through an optical system to obtain optical monitoring data, and combining the multi-source data to determine the internal crystallization state and impurity content of the solution, so as to perform scheduling execution when the crystallization state or impurity content deviates from the normal range;

[0038] A scheduling strategy adjustment module for feedbacking the optical monitoring data and the scheduling execution situation to the digital twin model based on the abnormal indication to correct the scheduling strategy and process parameters of the boric acid production line;

[0039] Among them, the multi-source data includes sensor data of temperature, flow rate, pH, and pressure installed at multiple key nodes on the boric acid production line. The preprocessing includes missing value filling and denoising filtering. The multi-objective scheduling model is used to output scheduling decisions according to scheduling requirements and resource lists.

[0040] The third aspect of the present invention discloses a terminal, including a processor and a storage medium; characterized in that:

[0041] The storage medium is used to store instructions;

[0042] The processor is used to operate according to the instructions to execute the steps of the method described in the first aspect.

[0043] The fourth aspect of the present invention discloses a computer-readable storage medium, on which a computer program is stored, characterized in that when the program is executed by a processor, it implements the steps of the method described in the first aspect.

[0044] The beneficial effects of the present invention are that, compared with the prior art, the present invention has the following advantages:

[0045] By acquiring multi-source sensor data from the boric acid production line and preprocessing the multi-source sensor data to map the preprocessed multi-source sensor data to the digital twin model. Then, extract the scheduling requirements of the current workshop from the initial parameters of the digital twin model and the preprocessed multi-source data vector, and construct a multi-objective scheduling model when the scheduling requirements meet the production requirements of the workshop. After that, the turbidity, crystal particle characteristics, and color change of the solution on the production line are monitored in real time through an optical system to obtain optical monitoring data, and the internal crystal state and impurity content of the solution are determined in combination with the multi-source data to perform scheduling execution when the crystal state or impurity content deviates from the normal range. Finally, based on the anomaly indication, the optical monitoring data and the scheduling execution situation are fed back to the digital twin model to correct the scheduling strategy and process parameters of the boric acid production line. This method corrects the scheduling strategy of the boric acid production line by integrating optical monitoring and multi-source sensor data. The sensor coverage rate is large and all are collected in real time, effectively avoiding the losses caused by the original scheduling strategy when abnormalities occur in boric acid production. The assistance of the digital twin model also improves the intelligence and production efficiency of boric acid production to a certain extent, ensuring the output and production quality of boric acid production. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 is a schematic structural diagram of a method for scheduling boric acid production materials based on the Internet of Things provided by the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0047] The present application will be further described below with reference to the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solutions of the present invention and cannot be used to limit the protection scope of the present application.

[0048] As Figure 1 shown, in one embodiment, an Internet of Things-based boric acid production material scheduling method includes the following steps:

[0049] Step S110: Obtain multi-source data from the boric acid production line and preprocess the multi-source data to map the preprocessed multi-source data to the digital twin model.

[0050] Among them, the multi-source data includes sensor data of temperature, flow rate, pH, and pressure installed at multiple key nodes on the boric acid production line. The preprocessing includes missing value filling and denoising filtering. The key nodes include the raw material warehouse, the conveying pipeline, and the reaction kettle.

[0051] In some embodiments, for the Internet of Things-based boric acid production material scheduling method provided by the present invention, step S110 specifically includes the following steps:

[0052] Step S111: Generate an original data vector based on the instantaneous readings of different sensors from the boric acid production line, and perform missing value filling and denoising filtering on the original data vector to obtain a preprocessed data vector.

[0053] Step S112: Determine key process variables based on the preprocessed data vector, and map the key process variables to the digital twin structure to build a digital twin model and obtain an initial parameter vector of the digital twin model.

[0054] Among them, the key process variables include temperature, boron ore impurity content, and flow rate. The initial parameter vector includes the initial modeling values of the reaction temperature, flow rate, and pH of the boric acid production line.

[0055] In some embodiments, for the Internet of Things-based boric acid production material scheduling method provided by the present invention, step S110 specifically further includes the following steps:

[0056] Step S113: Compare the established digital twin model with the actual monitoring data to obtain the error between the model output and the actual monitoring data, and determine whether the error exceeds the first threshold.

[0057] Step S114: When the error exceeds the first threshold, preprocess the initial parameters of the digital twin model again or correct the bias of the sensor to obtain the verification result of the digital twin model and the corrected model parameters.

[0058] Step S120: Extract the scheduling requirements of the current workshop from the initial parameters of the digital twin model and the preprocessed multi-source data vector. When the scheduling requirements meet the production requirements of the workshop, construct a multi-objective scheduling model.

[0059] Among them, the multi-objective scheduling model is used to output scheduling decisions according to the scheduling requirements and the resource list.

[0060] In some embodiments, for the boric acid production material scheduling method based on the Internet of Things provided by the present invention, step S120 specifically includes the following steps:

[0061] Step S121: Determine the key parameters of the total feeding amount, feeding frequency, and expected output according to the inventory data, flow rate, temperature, and pH of the boric acid production line in the digital twin model, and summarize and generate a scheduling requirement vector in combination with the workshop equipment capacity and personnel configuration.

[0062] Step S122: Set a multi-objective function for defining the decision variable vector, and obtain the scheduling decision variable vector based on the multi-objective function to construct a multi-objective scheduling model.

[0063] Among them, the multi-objective function includes minimizing the total transportation time, minimizing the energy consumption, and maximizing the production capacity utilization rate. The variable vector for decision-making includes the feeding time of all batches or the route selection of transportation vehicles within the scheduling decision number.

[0064] In some embodiments, for the boric acid production material scheduling method based on the Internet of Things provided by the present invention, step S120 specifically further includes the following steps:

[0065] Step S123: When the optical sensor monitors that the solution turbidity or crystal particle size is abnormal, trigger and transmit a first feedback signal through the data interaction interface between the multi-objective scheduling model and the optical system. When the multi-objective scheduling model captures the first feedback signal, fine-tune the corresponding feeding time or batch sequence.

[0066] Step S124: When the crystallization rate of the current feeding batch exceeds the second threshold, trigger and transmit a second feedback signal. When the multi-objective scheduling model captures the second feedback signal, delay the subsequent material conveying time or reduce the single feeding amount.

[0067] Step S125: Construct an adaptive function based on the first feedback signal and the second feedback signal to obtain a revised scheduling decision on the basis of the original adjustment strategy according to the adaptive function. The revised scheduling decision is used to generate a scheduling execution instruction.

[0068] Step S130, the turbidity, crystal particle characteristics, and color change of the solution on the production line are monitored in real time through an optical system to obtain optical monitoring data, and the internal crystal state and impurity content of the solution are determined by combining multi-source data, so as to perform scheduling execution when the crystal state or impurity content deviates from the normal range.

[0069] In some embodiments, for the boric acid production material scheduling method provided by the present invention, step S130 specifically includes the following steps:

[0070] Step S131, the turbidity, crystal particle characteristics, and color change of the solution are monitored in real time according to the set sampling frequency through an optical sensor installed at the outlet of the reaction kettle or the entrance of the crystallization workshop to obtain an optical data vector, and the optical data vector is fused with multi-source data to construct a fusion vector.

[0071] Step S132, an anomaly detection is performed on the fusion vector by calling a set normal working range threshold or a machine learning algorithm, and when the fusion vector shows an anomaly, the control system is triggered for early warning and automatic adjustment to generate an anomaly metric.

[0072] Step S133, a defined control strategy function is obtained based on the anomaly metric and the correction amount of the original adjustment strategy, and when the anomaly metric is a first value, the production scheduling variables are revised through a digital twin model to obtain a revised scheduling plan.

[0073] Step S140, based on the anomaly indication, the optical monitoring data and the scheduling execution situation are fed back to the digital twin model to correct the scheduling strategy and process parameters of the boric acid production line.

[0074] In some embodiments, for the boric acid production material scheduling method provided by the present invention, step S140 specifically includes the following steps:

[0075] Step S141, an execution instruction and an execution data log are obtained based on the revised scheduling plan, and a historical data matrix is constructed by combining the anomaly record and the optical monitoring data, so as to predict the crystal state or energy consumption situation at different times based on the historical data matrix by using a machine learning model.

[0076] Step S142, the scheduling strategy and the optical threshold are optimized based on the prediction result of the machine learning model to construct an optimization objective function, obtain updated new model parameters, and map the new model parameters to the digital twin model.

[0077] The above-mentioned boric acid production material scheduling method based on the Internet of Things obtains multi-source sensor data from the boric acid production line, preprocesses the multi-source sensor data, and maps the preprocessed multi-source sensor data to the digital twin model. Then, the scheduling requirements of the current workshop are extracted from the initial parameters of the digital twin model and the preprocessed multi-source data vector. When the scheduling requirements meet the production requirements of the workshop, a multi-objective scheduling model is constructed. After that, the turbidity, crystal particle characteristics, and color changes of the solution on the production line are monitored in real time through an optical system to obtain optical monitoring data. The internal crystal state and impurity content of the solution are determined by combining the multi-source data. When the crystal state or impurity content deviates from the normal range, scheduling execution is carried out. Finally, based on the anomaly indication, the optical monitoring data and the scheduling execution situation are fed back to the digital twin model to correct the scheduling strategy and process parameters of the boric acid production line. This method corrects the scheduling strategy of the boric acid production line by fusing optical monitoring and multi-source sensor data. The sensor coverage rate is large and all are collected in real time, effectively avoiding the losses caused by the original scheduling strategy when abnormalities occur in boric acid production. The assistance of the digital twin model also improves the intelligence and production efficiency of boric acid production to a certain extent, ensuring the output and production quality of boric acid production.

[0078] In a specific embodiment, the boric acid production material scheduling method based on the Internet of Things provided by the present invention includes steps 1 to 4:

[0079] Step 1, multi-source data collection and digital twin model initialization.

[0080] Establish a complete data foundation for the boric acid production line, lay a data foundation for subsequent material scheduling and optical monitoring, address the deficiencies of traditional single instrument data with insufficient coverage and long collection cycles, and ensure full data coverage and high-frequency sampling.

[0081] Specifically, it includes steps 1.1 to 1.4:

[0082] Step 1.1, sensor layout and raw data acquisition.

[0083] Specifically, various sensors such as temperature, flow rate, pH, and pressure are installed at multiple key nodes such as raw material warehouses, conveying pipelines, and reaction kettles to ensure full coverage of all major links in boric acid production. Then, a raw data vector is generated based on the collected sensor readings. The raw data vector is composed of instantaneous readings of different sensors (updated in real time, such as once per minute).

[0084] Step 1.2, data cleaning and preprocessing.

[0085] Specifically, the original data vector is preprocessed by means of missing value filling, denoising filtering, etc. to generate a clean and stable data vector composed of reliable readings obtained after cleaning. For significantly abnormal sampling points, the mean value or the Huadong median can be used for correction to avoid the influence of extreme values on subsequent analysis.

[0086] Step 1.3, Parameter mapping and digital twin structure construction.

[0087] Specifically, based on the preprocessed data vector, important process variables (such as temperature, boron ore impurity content, and flow rate, etc.) are determined and mapped to the corresponding modules of the digital twin. The initial state of each sub-module in the digital twin can be recorded as an initial parameter vector, including the initial modeling values of reaction temperature, flow rate, and pH, which are used to establish the digital twin model.

[0088] Step 1.4, System preliminary verification.

[0089] Specifically, the established digital twin model is compared with some monitoring data on the workshop site to ensure that the fitting deviation is within an acceptable range. If the deviation exceeds the set threshold range, return to Step 1.2 to adjust the data preprocessing strategy or correct the sensor offset to obtain the verification result of the digital twin and the corrected parameters.

[0090] Step 2, Material scheduling optimization and adaptive scheduling.

[0091] On the premise of meeting the quality requirements of boric acid products in multiple production lines and different batches, the transportation route and feeding time sequence are dynamically optimized to solve the defects that manual scheduling is difficult to respond to demand changes or material shortages in a timely manner.

[0092] Specifically, it includes Steps 2.1 to 2.4:

[0093] Step 2.1, Scheduling demand extraction and data input.

[0094] Specifically, the current actual demand, inventory status, and production target of the workshop are extracted from the initial parameters of the digital twin model and the preprocessed data vector to form a scheduling demand list. According to the information about inventory, flow rate, temperature, etc. in the digital twin model, key parameters such as the total feeding amount, feeding frequency, and expected output are determined, and combined with the equipment capacity and personnel configuration of the workshop, a scheduling demand vector is summarized. Among them, the scheduling demand vector is jointly composed of the demand for a single batch of boron ore or borax, the process time limit, and the target output. In addition, the data in the scheduling demand vector can also be updated in real time from the digital twin model, or obtained by mapping the targets issued by the management layer to the digital twin model.

[0095] Step 2.2, Multi-objective scheduling model construction.

[0096] Specifically, on the premise of meeting production requirements, taking into account transportation costs, energy consumption, and the need for real-time monitoring of subsequent optical systems, a scheduling optimization model is constructed. First, multi-objective functions are set, such as minimizing the total transportation time, minimizing energy consumption, and maximizing production capacity utilization for trade-offs. A variable vector for decision-making is defined, including the feeding time of any batch within the possible number of scheduling decisions or the route selection of transport vehicles.

[0097] Step 2.3, Adaptive scheduling is linked with the optical system.

[0098] Specifically, the scheduling decision is combined with the optical monitoring system, enabling the schedule to be dynamically adjusted according to real-time optical signal feedback. First, a data interaction interface with the optical monitoring system is reserved inside the scheduling optimization model: when the optical sensor detects abnormal solution turbidity or crystal particle size, a feedback signal can be triggered. After the scheduling optimization model captures the feedback signal, it makes minor adjustments to some feeding times or batch sequences to avoid continuous large-scale feeding when abnormal conditions occur. If the crystallization rate of the current batch is too fast, the scheduling optimization model can delay the subsequent material delivery time or reduce the single feeding amount. An adaptive function is constructed based on the optical monitoring feedback to calculate the new decision vector revised on the basis of the original scheduling strategy. Through the above linkage, the scheduling revision can be automatically triggered during process abnormalities to reduce losses and stabilize production.

[0099] For example, when the scheduling system receives the optical feedback "abnormal precipitation detected", the feeding time of subsequent batches can be postponed by 10 - 20 minutes, or the feeding amount can be reduced, so that the staff can handle the crystallization situation.

[0100] Step 2.4, Model solution and implementation.

[0101] Specifically, the above multi-objective scheduling model and adaptive strategy are implemented in actual production. A suitable algorithm (improved particle swarm, genetic algorithm, or heuristic algorithm in edge computing) is selected for solution, and a scheduling plan is made according to the solution result.

[0102] In this embodiment, different solution strategies are selected according to the calculation scale, network bandwidth, and workshop real-time requirements. For example, if high precision is required, an evolutionary algorithm can be used in the cloud; if fast response is needed, a simplified heuristic algorithm can be deployed at the edge. Once the optimal solution or sub-optimal solution is confirmed, the logistics equipment, feeding devices, etc. are called in the order shown by the scheduling strategy before and after revision. If an abnormal signal from the optical monitoring system is received subsequently, the current scheduling strategy is revised. Finally, during the execution of the schedule, the process data during execution needs to be recorded in real time and fed back to the digital twin model for model optimization.

[0103] Step 3, Real-time control of the production process integrating optical monitoring.

[0104] An optical system is introduced to finely detect the turbidity, refractive index, spectral characteristics, etc. of the boric acid solution to achieve early anomaly recognition.

[0105] Specifically, it includes steps 3.1 to 3.4:

[0106] Step 3.1, Arrangement of the optical monitoring device and data acquisition.

[0107] Specifically, optical sensors (visible light, infrared light, laser scattering, etc.) are installed in the reaction kettle, crystallization tank or key pipelines to monitor the turbidity of the solution, the characteristics of crystal particles and the color change in real time. Among them, the arrangement position of the optical sensor is preferably selected at key points such as the outlet of the reaction kettle or the entrance of the crystallization workshop where the crystallization state is easy to observe. If the volume of the reaction kettle is large, multiple optical probes can be installed at different heights. In addition, the sampling frequency of the optical sensor can be set in the range of 1 s to 30 s according to the production rhythm to ensure sufficient time resolution. Finally, a corresponding optical data vector is constructed based on the arrangement position and sampling frequency of the optical sensor, including light transmittance, light scattering intensity and other optical characteristics (such as the intensity of infrared absorption peaks). The above optical monitoring data helps to judge the particle size and impurity content in the solution.

[0108] Step 3.2, Optical data fusion and anomaly recognition.

[0109] Specifically, the optical data vector is fused with the existing multi-source sensor data to comprehensively judge the crystallization and impurity conditions inside the solution and timely detect abnormal conditions that deviate from the normal range. First, a fusion vector is constructed based on the optical data vector and the aforementioned sensor data, so that all elements in the fusion vector are synchronously collected at the same time point for real-time analysis. Subsequently, the threshold of the normal working range is set. For example, the optical transmittance in the range of 0.8 to 1 is the normal working range, and an algorithm based on the normal working range threshold or machine learning is used to detect anomalies in the fusion vector. Once an anomaly is identified, the control system can be triggered for early warning or automatic adjustment to avoid the decline of production volume or production quality caused by excessive crystallization or impurity aggregation, and at the same time, a corresponding anomaly indication quantity is output.

[0110] Step 3.3, Control strategy linked to the material scheduling.

[0111] Specifically, when an anomaly is detected (such as early crystallization or impurity enrichment), the feeding rate or material transportation time can be dynamically adjusted to achieve adaptive linkage control. First, a control strategy function is defined based on the anomaly indication quantity and the revised quantity of the original scheduling strategy (such as delaying the feeding time and reducing the feeding batch). When the anomaly indication quantity is not 0, the production impact is verified through the digital twin model, and then the scheduling variables are revised to obtain a new revised schedule to ensure that the production process is not out of control due to the occurrence of anomalies. If the optical monitoring repeatedly indicates that the solution turbidity is too high, the feeding system can be instructed to suspend the addition of the next batch of boron ore or sulfuric acid, and increase the stirring or raise the solution flow rate to accelerate the sedimentation of impurities.

[0112] Step 3.4, execution and closed-loop feedback.

[0113] Specifically, the scheduling correction and control instructions are conveyed to the on-site execution layer (such as automatic valves, pumps, agitators, etc.), and the execution results are fed back to the digital twin model to form a complete closed-loop control. First, the revised new schedule and control strategy are sent to the corresponding equipment through the PLC system or DCS system, including specific instructions such as switching valves, adjusting stirring, and controlling the feeding quantity. After that, the temperature, pH, and optical monitoring data after actual operation are again subjected to anomaly detection. If anomalies still exist, the current schedule is revised again. If it has returned to normal, the next batch of feeding production continues according to the current established schedule. Finally, all data of the current batch process control (such as the moment of anomaly occurrence and response measures) are recorded, and the recorded data are synchronized to the digital twin model for model optimization.

[0114] Step 4, iterative evolution of the scheduling system.

[0115] The data of real-time monitoring and scheduling execution are transmitted back to the digital twin and machine learning models to form a closed loop, so as to continuously correct and upgrade the scheduling strategy and process parameters.

[0116] Specifically, it includes steps 4.1 to 4.3:

[0117] Step 4.1, data collection and historical record archiving.

[0118] Specifically, a historical data matrix is constructed based on all the data (control data logs, anomaly records, and optical monitoring data) recorded and transmitted in step 3.4 and the current scheduling execution results for subsequent model learning or statistical analysis.

[0119] Step 4.2, algorithm training and parameter update.

[0120] Specifically, a machine learning model (such as LSTM or random forest) is used to predict the crystallization state or energy consumption at different times, and based on this, the scheduling decision or optical threshold is optimized, and the corresponding objective optimization function is defined. The defined objective optimization function is jointly determined by the output of boric acid production, total energy consumption, abnormal shutdown duration, and their respective adjustable weight coefficients. Finally, through training, the process and scheduling strategy that maximize the objective optimization function are found, and at the same time, the updated model parameters (such as the best feeding frequency, improved threshold) are obtained.

[0121] Step 4.3, Digital Twin Revision and Simulation Verification.

[0122] Specifically, the core equation in the Digital Twin model is tuned according to the updated parameters to ensure that the virtual factory closely corresponds to the real factory. A round of simulated production can be executed in the simulation environment to observe whether the curves of the finished product quality, energy consumption, and optical monitoring values match the expected results. If the error between the expected results predicted by the revised Digital Twin and the real workshop does not exceed the set threshold, it indicates that the current scheduling revision is successful.

[0123] The boric acid production material scheduling system based on the Internet of Things provided by the present invention will be described below. The boric acid production material scheduling system based on the Internet of Things described below can be mutually referred to the boric acid production material scheduling method described above.

[0124] In one embodiment, a boric acid production material scheduling system based on the Internet of Things includes a data preprocessing module, a model construction module, a scheduling execution module, and a scheduling strategy adjustment module.

[0125] The data preprocessing module is used to obtain multi-source data from the boric acid production line and preprocess the multi-source data to map the preprocessed multi-source data to the Digital Twin model.

[0126] The model construction module is used to extract the scheduling requirements of the current workshop from the initial parameters of the Digital Twin model and the preprocessed multi-source data vector, and construct a multi-objective scheduling model when the scheduling requirements meet the workshop production requirements.

[0127] The scheduling execution module is used to monitor the turbidity, crystal particle characteristics, and color change of the solution on the production line in real time through the optical system to obtain optical monitoring data, and determine the internal crystallization state and impurity content of the solution in combination with the multi-source data, so as to perform scheduling execution when the crystallization state or impurity content deviates from the normal range.

[0128] The scheduling strategy adjustment module is used to feedback the optical monitoring data and the scheduling execution situation to the Digital Twin model based on the abnormal indication to correct the scheduling strategy and process parameters of the boric acid production line.

[0129] Among them, the multi-source data includes sensor data of temperature, flow rate, pH, and pressure installed at multiple key nodes on the boric acid production line. The preprocessing includes missing value filling and denoising filtering. The multi-objective scheduling model is used to output scheduling decisions according to scheduling requirements and resource lists.

[0130] In this embodiment, for the boric acid production material scheduling system based on the Internet of Things provided by the present invention, the data preprocessing module is specifically used for:

[0131] Generating an original data vector based on the instantaneous readings of different sensors from the boric acid production line, and performing missing value filling and denoising filtering on the original data vector to obtain a preprocessed data vector.

[0132] Determining key process variables based on the preprocessed data vector, and mapping the key process variables into the digital twin structure to build a digital twin model and obtain an initial parameter vector of the digital twin model.

[0133] Among them, the key process variables include temperature, boron ore impurity content, and flow rate, and the initial parameter vector includes the initial modeling values of the reaction temperature, flow rate, and pH of the boric acid production line.

[0134] In this embodiment, for the boric acid production material scheduling system based on the Internet of Things provided by the present invention, the data preprocessing module is specifically further used for:

[0135] Comparing the established digital twin model with the actual monitoring data to obtain the error between the model output and the actual monitoring data, and determining whether the error exceeds the first threshold.

[0136] When the error exceeds the first threshold, the initial parameters of the digital twin model are preprocessed again or the bias of the sensor is corrected to obtain the verification result of the digital twin model and the corrected model parameters.

[0137] In this embodiment, for the boric acid production material scheduling system based on the Internet of Things provided by the present invention, the model construction module is specifically used for:

[0138] Determining the key parameters of the total feeding amount, feeding frequency, and expected output according to the inventory data, flow rate, temperature, and pH of the boric acid production line in the digital twin model, and summarizing and generating a scheduling requirement vector in combination with the workshop equipment capacity and personnel configuration.

[0139] Setting a multi-objective function for defining the decision variable vector, and obtaining a scheduling decision variable vector based on the multi-objective function to construct a multi-objective scheduling model.

[0140] Among them, the multi-objective function includes minimizing the total transportation time, minimizing the energy consumption, and maximizing the production capacity utilization rate, and the decision variable vector includes all batch feeding times or the route selection of transportation vehicles within the scheduling decision number.

[0141] In this embodiment, for the boric acid production material scheduling system based on the Internet of Things provided by the present invention, the model construction module is specifically further used for:

[0142] When the optical sensor monitors that the turbidity of the solution or the size of the crystal particles is abnormal, a first feedback signal is triggered and transmitted through the data interaction interface between the multi-objective scheduling model and the optical system. When the multi-objective scheduling model captures the first feedback signal, the corresponding feeding time or batch sequence is slightly adjusted.

[0143] When the crystallization rate of the current feeding batch exceeds the second threshold, a second feedback signal is triggered and transmitted. When the multi-objective scheduling model captures the second feedback signal, the subsequent material conveying time is postponed or the single feeding amount is reduced.

[0144] An adaptive function is constructed based on the first feedback signal and the second feedback signal, so as to obtain a revised scheduling decision based on the adaptive function on the basis of the original adjustment strategy. The revised scheduling decision is used to generate a scheduling execution instruction.

[0145] In this embodiment, for the boric acid production material scheduling system based on the Internet of Things provided by the present invention, the scheduling execution module is specifically used for:

[0146] The turbidity of the solution, the crystal particle characteristics and the color change are monitored in real time according to the set sampling frequency through the optical sensor installed at the discharge port of the reactor or the entrance of the crystallization workshop to obtain an optical data vector, and the optical data vector is fused with multi-source data to construct a fusion vector.

[0147] Anomaly detection is performed on the fusion vector by calling a set normal working range threshold or a machine learning algorithm. When the fusion vector is abnormal, the control system is triggered to give an early warning and automatic adjustment to generate an anomaly index quantity.

[0148] A defined control strategy function is obtained based on the anomaly index quantity and the correction quantity of the original adjustment strategy. When the anomaly index quantity is the first value, the production scheduling variables are revised through the digital twin model to obtain a revised scheduling plan.

[0149] In this embodiment, for the boric acid production material scheduling system based on the Internet of Things provided by the present invention, the scheduling strategy adjustment module is specifically used for:

[0150] An execution instruction and an execution data log are obtained based on the revised scheduling plan, and a historical data matrix is constructed in combination with the anomaly record and the optical monitoring data, so as to predict the crystallization state or energy consumption at different times based on the historical data matrix by using a machine learning model.

[0151] Optimize the scheduling strategy and optical threshold based on the prediction results of the machine learning model to construct an optimization objective function, obtain updated new model parameters, and map the new model parameters to the digital twin model.

[0152] This disclosure may be a system, method, and / or computer program product. The computer program product may include a computer-readable storage medium having computer-readable program instructions thereon for causing a processor to implement various aspects of this disclosure.

[0153] A computer-readable storage medium may be a tangible device that can retain and store instructions for use by an instruction execution device. A computer-readable storage medium may be, for example, but is not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disc (DVD), a memory stick, a floppy disk, a mechanically encoded device such as a punch card or raised structures in grooves having instructions stored thereon, and any suitable combination of the foregoing. The computer-readable storage medium as used herein is not to be construed as a transitory signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., an optical pulse through an optical fiber cable), or an electrical signal transmitted through a wire.

[0154] The computer-readable program instructions described herein may be downloaded from a computer-readable storage medium to various computing / processing devices, or may be downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network may include copper transmission cables, optical fiber transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in a computer-readable storage medium in each computing / processing device.

[0155] The computer program instructions for performing the operations of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine - related instructions, microcode, firmware instructions, state - setting data, or source code or object code written in any combination of one or more programming languages, including object - oriented programming languages such as Smalltalk, C++, etc., and conventional procedural programming languages such as the "C" language or similar programming languages. The computer - readable program instructions may be executed entirely on the user's computer, partially on the user's computer, executed as a stand - alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider). In some embodiments, by using the state information of the computer - readable program instructions to customize an electronic circuit, such as a programmable logic circuit, a field - programmable gate array (FPGA), or a programmable logic array (PLA), the electronic circuit can execute the computer - readable program instructions to implement various aspects of the present disclosure.

[0156] Aspects of the present disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the disclosure. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer - readable program instructions.

[0157] These computer - readable program instructions can be provided to a processor of a general - purpose computer, a special - purpose computer, or other programmable data - processing apparatus to produce a machine such that the instructions, when executed by the processor of the computer or other programmable data - processing apparatus, create a means for implementing the functions / acts specified in one or more blocks of the flowchart and / or block diagram. These computer - readable program instructions can also be stored in a computer - readable storage medium, which causes a computer, a programmable data - processing apparatus, and / or other devices to operate in a particular manner, so that the computer - readable medium storing the instructions comprises a manufacture including instructions for implementing various aspects of the functions / acts specified in one or more blocks of the flowchart and / or block diagram.

[0158] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices, causing a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other devices to generate a computer-implemented process, such that the instructions executed on the computer, other programmable data processing apparatus, or other devices implement the functions / acts specified in one or more boxes of the flowchart and / or block diagram.

[0159] The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, a segment of a program, or a portion of an instruction, which contains one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions noted in the blocks may occur out of the order noted in the figures. For example, two consecutive blocks may in fact be executed substantially in parallel, or they may sometimes be executed in the reverse order, depending on the functionality involved. It should also be noted that each block of the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented by a dedicated hardware-based system that performs the specified functions or acts, or by a combination of dedicated hardware and computer instructions.

[0160] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: modifications or equivalent replacements can still be made to the specific embodiments of the present invention, and any modifications or equivalent replacements that do not depart from the spirit and scope of the present invention should be covered by the protection scope of the claims of the present invention.

Claims

1. A boric acid production material scheduling method based on the Internet of Things, characterized in that: The method comprises: Acquire multi-source data from a boric acid production line, and pre-process the multi-source data to map the pre-processed multi-source data to a digital twin model; Extracting the scheduling requirements of the current workshop from the initial parameters of the digital twin model and the preprocessed multi-source data vector, and building a multi-objective scheduling model when the scheduling requirements meet the production requirements of the workshop; The turbidity, crystal particle characteristics and color changes of the solution on the production line are monitored in real time by an optical system to obtain optical monitoring data, and the crystal state and impurity content inside the solution are determined in combination with the multi-source data, so as to perform scheduling when the crystal state or impurity content deviates from the normal range; Feeding back the optical monitoring data and the scheduling execution status to the digital twin model based on the abnormal indication to correct the scheduling strategy and process parameters of the boric acid production line; Among them, the multi-source data includes sensor data of temperature, flow, pH and pressure installed at multiple key nodes on the boric acid production line, the preprocessing includes missing value filling and denoising filtering, and the multi-objective scheduling model is used to output scheduling decisions based on scheduling requirements and resource lists.

2. The method for material scheduling of boric acid production based on the Internet of Things according to claim 1, characterized in that: The step of acquiring multi-source data from a boric acid production line and preprocessing the multi-source data to map the preprocessed multi-source data to a digital twin model includes: Generating a raw data vector based on instantaneous readings from different sensors of the boric acid production line, and performing padding and denoising filtering on the raw data vector to obtain a preprocessed data vector; Determining key process variables based on the preprocessed data vector, and mapping the key process variables to the digital twin structure to build the digital twin model and obtain an initial parameter vector of the digital twin model; Among them, the key process variables include temperature, boron ore impurity content and flow rate, and the initial parameter vector includes the initial modeling values ​​of the reaction temperature, flow rate and pH of the boric acid production line.

3. The method for material scheduling of boric acid production based on the Internet of Things according to claim 2, characterized in that: The method of acquiring multi-source data from a boric acid production line and preprocessing the multi-source data to map the preprocessed multi-source data to a digital twin model further includes: Compare the established digital twin model with the actual monitoring data to obtain the error between the model output and the actual monitoring data, and determine whether the error exceeds a first threshold; When the error exceeds the first threshold, the initial parameters of the digital twin model are preprocessed again or the bias of the sensor is corrected to obtain the verification result of the digital twin model and the corrected model parameters.

4. The method for material scheduling of boric acid production based on the Internet of Things according to claim 3, characterized in that: The extracting the scheduling requirements of the current workshop from the initial parameters of the digital twin model and the preprocessed multi-source data vector, and constructing a multi-objective scheduling model when the scheduling requirements meet the production requirements of the workshop, includes: According to the inventory data, flow rate, temperature and pH of the boric acid production line in the digital twin model, the total amount of feed, feeding frequency and key parameters of the expected output are determined, and the scheduling demand vector is generated in combination with the workshop equipment capacity and personnel configuration; Setting a multi-objective function for defining a decision variable vector, and obtaining a scheduling decision variable vector based on the multi-objective function to construct the multi-objective scheduling model; The multi-objective function includes minimizing the total transportation time, minimizing the energy consumption and maximizing the capacity utilization, and the variable vector for decision-making includes all batch feeding times or route selections of transportation vehicles within the scheduling decision number.

5. The method for material scheduling of boric acid production based on the Internet of Things according to claim 4, characterized in that: The method further comprises extracting the scheduling requirements of the current workshop from the initial parameters of the digital twin model and the preprocessed multi-source data vector, and constructing a multi-objective scheduling model when the scheduling requirements meet the production requirements of the workshop, and further comprising: When the optical sensor monitors that the solution turbidity or the crystal particle size is abnormal, a first feedback signal is triggered and transmitted through the data interaction interface between the multi-objective scheduling model and the optical system, and when the multi-objective scheduling model captures the first feedback signal, the corresponding feeding time or batch sequence is fine-tuned; When the crystallization rate of the current batch of materials exceeds a second threshold, a second feedback signal is triggered and transmitted, and when the multi-objective scheduling model captures the second feedback signal, the subsequent material delivery time is delayed or the single feeding amount is reduced; An adaptive function is constructed based on the first feedback signal and the second feedback signal to obtain a revised scheduling decision based on the original adjustment strategy according to the adaptive function, and the revised scheduling decision is used to generate a scheduling execution instruction.

6. The method for material scheduling of boric acid production based on the Internet of Things according to claim 5, characterized in that: The method comprises: monitoring the turbidity, crystal particle characteristics and color changes of the solution on the production line in real time through the optical system to obtain optical monitoring data, and determining the crystal state and impurity content inside the solution in combination with the multi-source data, so as to perform scheduling when the crystal state or impurity content deviates from the normal range, including: According to the set sampling frequency, the turbidity, crystal particle characteristics and color change of the solution are monitored in real time by an optical sensor installed at the discharge port of the reactor or the entrance of the crystallization workshop to obtain an optical data vector, and the optical data vector is fused with the multi-source data to construct a fusion vector; Calling a normal working range threshold or a machine learning algorithm to perform abnormality detection on the fusion vector, and triggering a control system to perform early warning and automatic adjustment when an abnormality occurs in the fusion vector, so as to generate an abnormality indicator; A defined control strategy function is obtained based on the abnormal indicator and the correction amount to the original adjustment strategy, and when the abnormal indicator is a first value, the production scheduling variable is revised through the digital twin model to obtain a revised scheduling plan.

7. The method for material scheduling of boric acid production based on the Internet of Things according to claim 6, characterized in that: The method of feeding back the optical monitoring data and the scheduling execution status to the digital twin model based on the abnormal indication to correct the scheduling strategy and process parameters of the boric acid production line includes: Acquire execution instructions and execution data logs based on the revised scheduling plan, and construct a historical data matrix in combination with abnormal records and optical monitoring data, so as to use a machine learning model to predict the crystallization state or energy consumption at different times based on the historical data matrix; The scheduling strategy and optical threshold are optimized based on the prediction results of the machine learning model to construct an optimization objective function, obtain updated new model parameters, and map the new model parameters to the digital twin model.

8. A boric acid production material scheduling system based on the Internet of Things, characterized in that: The system comprises: A data preprocessing module, used for acquiring multi-source data from a boric acid production line and preprocessing the multi-source data to map the preprocessed multi-source data to a digital twin model; A model building module, used to extract the scheduling requirements of the current workshop from the initial parameters of the digital twin model and the preprocessed multi-source data vector, and to build a multi-objective scheduling model when the scheduling requirements meet the production requirements of the workshop; A scheduling execution module, which is used to monitor the turbidity, crystal particle characteristics and color changes of the solution on the production line in real time through an optical system to obtain optical monitoring data, and determine the crystal state and impurity content inside the solution in combination with the multi-source data, so as to perform scheduling execution when the crystal state or impurity content deviates from a normal range; A scheduling strategy adjustment module, used to feed back the optical monitoring data and scheduling execution status to the digital twin model based on abnormal indications to correct the scheduling strategy and process parameters of the boric acid production line; Among them, the multi-source data includes sensor data of temperature, flow, pH and pressure installed at multiple key nodes on the boric acid production line, the preprocessing includes missing value filling and denoising filtering, and the multi-objective scheduling model is used to output scheduling decisions based on scheduling requirements and resource lists.

9. A terminal comprising a processor and a storage medium; characterized in that: The storage medium is used to store instructions; The processor is configured to operate according to the instructions to execute the steps of the method according to any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images