Auxiliary material adding control system for throat lozenge production

Abstract

The invention discloses a throat lozenge production auxiliary material adding control system, and belongs to the technical field of data modeling and analysis, and the throat lozenge production auxiliary material adding control system comprises a threshold matrix establishment module which is used for constructing a dynamic threshold matrix; the data acquisition module is used for acquiring current production data; the data analysis module is used for generating a mode selection signal according to a comparison result of the current production data and the dynamic threshold matrix; the mode selection module is used for activating a corresponding control mode based on the mode selection signal, and the control mode comprises a conventional mode, an adjustment mode and an exception handling mode; and the control execution module is used for executing a control instruction corresponding to the control mode and sending the verified control instruction to the auxiliary material adding execution mechanism. According to the method, intelligent association and control strategy optimization of multi-source heterogeneous data are realized through data modeling and iterative optimization of an algorithm level.

Description

Technical Field

[0001] The invention relates to the technical field of data modeling and analysis, and in particular to a control system for adding auxiliary materials to throat lozenge production. Background Art

[0002] In the existing field of intelligent control of food industry production, computer-based data processing methods are widely used in process optimization. However, the current control strategy has significant technical bottlenecks when it comes to adding auxiliary materials to special foods such as throat lozenges.

[0003] At present, traditional methods use linear weighted or static correlation models to process multi-source heterogeneous data, such as sensor time series data and process maps, resulting in insufficient cross-modal feature fusion; dynamic threshold setting relies on fixed rules, such as Z-Score statistics, which is difficult to adapt to the time-varying characteristics of the production line, causing mode switching hysteresis and parameter oscillation; the simulation verification system ignores equipment dynamic errors, such as servo inertia delay, resulting in deviations between virtual simulation and actual execution; the time series prediction model is not robust enough to nonlinear interference, and the fixed time window strategy does not match the production rhythm, resulting in compensation drift; there is a lack of knowledge transfer across control modes, and parameter inheritance relies on manual configuration, which reduces the efficiency of fault tracing. Summary of the invention

[0004] In order to solve the above problems, the present invention provides a control system for adding auxiliary materials to the production of throat lozenges, which realizes intelligent association and control strategy optimization of multi-source heterogeneous data through data modeling and iterative optimization at the algorithm level.

[0005] The above objectives can be achieved through the following solutions: A control system for adding auxiliary materials to the production of throat lozenges, comprising a threshold matrix establishment module for constructing a dynamic threshold matrix, wherein the dynamic threshold matrix includes a viscosity reference value, a sugar content floating range, and an interval range of temperature and humidity critical points; a data acquisition module for collecting current production data, wherein the production data includes viscosity sensor measurement values ​​of a raw material conveying section, auxiliary material bin temperature and humidity monitoring data, and finished product online detection indicators; a data analysis module for generating a mode selection signal based on a comparison result between the current production data and the dynamic threshold matrix; a mode selection module for activating a corresponding control mode based on the mode selection signal, wherein the control mode includes a normal mode, an adjustment mode, and an exception handling mode; and a control execution module for executing a control instruction corresponding to the control mode, and sending the verified control instruction to an auxiliary material addition execution mechanism.

[0006] Optionally, the data analysis module includes: a deviation analysis unit, used to calculate the deviation of each indicator in the current production data relative to the dynamic threshold matrix; an abnormality judgment unit, used to trigger the abnormality handling mode when it is detected that the deviation of at least one indicator exceeds a preset warning value; an adjustment judgment unit, used to trigger the adjustment mode when the deviation of all indicators is within a preset adjustment range; a normal judgment unit, used to maintain the normal mode when the deviation of all indicators does not exceed a preset allowable fluctuation range.

[0007] Optionally, the adjustment mode includes: retrieving a set of historical parameters in historical production batches that matches the current deviation; calculating a dynamic compensation coefficient for the auxiliary material addition rate based on the set of historical parameters; and superimposing the dynamic compensation coefficient on the current formula parameters to generate corrected control parameters.

[0008] Optionally, the calculation of the dynamic compensation coefficient of the auxiliary material addition rate includes: establishing a sliding time window, the length of which is 10% of the length of the current production batch; extracting the historical parameter change rate within the sliding time window, and calculating the predicted compensation amount; weightedly fusing the predicted compensation amount with the conventional compensation amount, and outputting the final dynamic compensation coefficient.

[0009] Optionally, the exception handling mode includes: extracting control parameters of three processes preset for the current production batch; performing multi-dimensional feature matching of the control parameters with a historical fault case library; and generating processing instructions including equipment calibration priority and recipe reset solutions based on the matching results.

[0010] Optionally, the multi-dimensional feature matching of the control parameters with the historical fault case library includes: constructing a three-dimensional weight matrix of the current abnormal features, the three-dimensional weight matrix including parameter deviation, equipment aging coefficient and environmental interference factor; calculating the feature similarity between the three-dimensional weight matrix and the historical fault cases; and selecting the processing strategy corresponding to the historical case with the highest feature similarity as the basic template.

[0011] Optionally, sending the verified control instruction to the auxiliary material addition actuator includes: creating a digital twin model of the auxiliary material addition process; loading the control instruction and real-time environmental parameters in the digital twin model; obtaining quality prediction indicators of the virtual finished product after simulation operation; when the deviation between the quality prediction indicator and the preset standard is less than an allowable threshold, confirming that the control instruction is valid.

[0012] Optionally, the simulation operation includes: aligning the timing labels of the actual production line and the digital twin model; adding random disturbance factors to simulate equipment execution errors; recording the data fluctuation range of the simulation process and generating a safety verification report.

[0013] Optionally, the calculation of the predicted compensation amount includes: obtaining the changing trend of ambient temperature and humidity in the next 15 minutes; predicting the change of auxiliary material demand using a long short-term memory neural network; and correcting the length and weight distribution of the sliding time window based on the prediction results.

[0014] Based on the same inventive concept, the present invention also provides a method for controlling the addition of auxiliary materials in the production of throat lozenges, the method comprising: constructing a dynamic threshold matrix, the dynamic threshold matrix comprising a viscosity reference value, a sugar content floating range, and an interval range of temperature and humidity critical points; collecting current production data, the production data comprising viscosity sensor measurement values ​​of the raw material conveying section, auxiliary material bin temperature and humidity monitoring data, and finished product online detection indicators; generating a mode selection signal based on a comparison result between the current production data and the dynamic threshold matrix; activating a corresponding control mode based on the mode selection signal, the control mode comprising a normal mode, an adjustment mode, and an exception handling mode; executing a control instruction corresponding to the control mode, and sending the verified control instruction to an auxiliary material addition actuator.

[0015] Compared with the prior art, the present invention has the following advantages: 1. By constructing a dynamic threshold matrix of viscosity, sugar content, temperature and humidity parameters, combined with multi-level deviation analysis, intelligent decision-making from normal mode to abnormal mode is achieved; its advantage lies in overcoming the rigidity of the traditional fixed threshold system, and through dynamic adaptation of process parameters, the compensation strategy is quickly activated when the ambient temperature and humidity suddenly change or the raw material batch fluctuates, thus reducing the deviation of auxiliary material ratio caused by response delay; 2. Hypergraph neural network and improved tensor decomposition technology are used to perform multimodal fusion of sensor time series data, process maps and environmental parameters to analyze the implicit correlation rules of cross-domain data. Compared with the traditional static weighted model, this technology expands the feature correlation dimension to three times, and the computational complexity maintains a linear growth. Assisted by the LSTM-enhanced sliding window prediction mechanism, it can predict the trend of auxiliary material demand changes 15 minutes in advance, so that the calculation accuracy of the compensation coefficient is improved, which is especially suitable for the seasonal parameter drift scenario of the production process. 3. Based on the incremental digital twin, a bidirectional channel of virtual and real data is constructed to simulate dynamic errors such as equipment inertia delay and mechanical wear before command execution, and generate multi-condition test plans through Monte Carlo perturbation injection; this technology compresses the execution deviation rate between the virtual simulation verification results and the actual production line, avoiding resource waste under the traditional trial and error mechanism; the system uses the timing alignment algorithm and the three-dimensional visualization feedback mechanism to accurately locate potential process defects, greatly shortening the abnormal response time; 4. In the exception handling mode, a three-dimensional weight matrix is ​​used for multi-dimensional feature matching, combined with the case library retrieval technology driven by reinforcement learning, to generate a priority list for equipment calibration and a formula reset solution; the efficiency of fault diagnosis is improved, and the occurrence rate of secondary faults is reduced through a dynamic weight allocation strategy, especially in complex abnormal scenarios such as mixed temperature out of control and metering pump blockage. 5. Design a parameter inheritance engine driven by deep reinforcement learning, establish a weight migration channel between modes through the Q-learning strategy, and ensure that the dynamic compensation coefficient of the adjustment mode can be seamlessly inherited to the abnormal backtracking model; cooperate with the progressive switching strategy and double buffering mechanism to eliminate the parameter jump during the switching of the traditional system, reduce the mechanical impact during the transition of the control command, and extend the service life of the actuator.

[0016] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures pointed out in the description, claims and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 The present invention is a framework diagram of a control system for adding auxiliary materials to throat lozenge production according to an embodiment of the present invention.

[0019] Figure 2 The present invention is a schematic diagram of the structure of a control system for adding auxiliary materials to throat lozenges in an embodiment of the present invention.

[0020] Figure 3 The present invention is a flowchart of a method for controlling the addition of auxiliary materials for producing throat lozenges according to an embodiment of the present invention. DETAILED DESCRIPTION

[0021] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0022] Reference Figure 1 An embodiment of the present invention proposes a control system for adding auxiliary materials to throat lozenge production, which realizes intelligent association and control strategy optimization of multi-source heterogeneous data through data modeling and iterative optimization at the algorithm level.

[0023] The system of this embodiment specifically includes: A threshold matrix building module is used to build a dynamic threshold matrix, wherein the dynamic threshold matrix includes a viscosity reference value, a sugar content floating range, and an interval range of temperature and humidity critical points; Specifically, the dynamic threshold matrix is ​​a multi-dimensional parameter set covering the entire production process, including the interval definition of the viscosity reference value, sugar content floating range, and temperature and humidity critical points. The viscosity reference value is the standard reference value of the viscosity during the raw material dissolution stage during the production process, and is dynamically adjusted according to the characteristics of the raw material batch. The sugar content floating range is the maximum allowable fluctuation range of the finished product sugar content, which is related to the percentage deviation of the target sugar content. The temperature and humidity critical points are the safe and stable boundary values ​​of the auxiliary material storage environment, which control the maintenance conditions of the auxiliary material active substances.

[0024] The viscosity reference value is calculated by the median of the viscosity sensor in the sliding time window, the window length L = 60 minutes, and temperature and humidity compensation are taken into account. ,have , In the formula, is the median viscosity value in the past 60 minutes, is the temperature and humidity compensation coefficient, It is the difference between the current temperature and the reference temperature. Temperature and humidity compensation coefficient The value range is 0.005≤ ≤0.02, and calibrated by orthogonal experimental method.

[0025] For floating range ,have , In the formula, is the mean value within the statistical period, is the standard deviation within the statistical period, Dynamically adjusted according to the production stage.

[0026] A data acquisition module is used to collect current production data, including viscosity sensor measurement values ​​of the raw material conveying section, temperature and humidity monitoring data of the auxiliary material bin, and online detection indicators of finished products; Specifically, the viscosity sensor measurement value is a physical indicator for real-time monitoring of the flow resistance of the mixed liquid in the raw material delivery pipeline, reflecting the uniformity and dissolution state of the raw materials. The auxiliary material warehouse temperature and humidity monitoring data is the auxiliary material storage environment temperature and humidity parameters collected by distributed sensors, which are used to evaluate the preservation activity of auxiliary materials. The finished product online detection index is the physical and chemical parameters of the finished throat lozenges obtained in real time by a spectrometer or near-infrared detector, including sugar content uniformity and hardness value.

[0027] Among them, the viscosity sensor uses Brookfield DV2T type, with a measurement accuracy of ±1%FS; the temperature and humidity sensor uses Sensirion SHT35, with a temperature of ±0.3℃ and a humidity of ±2%RH; the metering pump control resolution reaches 0.01mL / pulse. The metering pump communicates with the control system through the Modbus RTU protocol, and the instruction format is: {starting address 0x01; function code 0x06; register address 0x2000; flow rate setting value (unit 0.01mL / s)}, and the CRC check code is generated using the Modbus standard algorithm.

[0028] A data analysis module, configured to generate a mode selection signal according to a comparison result between the current production data and the dynamic threshold matrix; Specifically, the comparison result is a comprehensive evaluation result formed by the data analysis module through data fusion technology, which matches the current data with the threshold in multiple dimensions. The mode selection signal is a set of instructions including mode priority and response strategy, which is determined by the weight distribution of the deviation degree.

[0029] A mode selection module, configured to activate a corresponding control mode based on the mode selection signal, wherein the control mode includes a normal mode, an adjustment mode, and an abnormality handling mode; Specifically, the normal mode is a standard operation mode in which production parameters are within the threshold range, and the pre-stored standardized formula parameters are directly called. The adjustment mode is a dynamic compensation mode when it is detected that the benchmark threshold is exceeded but the warning value is not reached, triggering historical parameter backtracking and predictive compensation. The abnormal handling mode is an emergency response mode when it is detected that the key parameters reach the warning threshold, and the fault tracing analysis and disposal plan generation are initiated.

[0030] The control execution module is used to execute the control instructions corresponding to the control mode and send the verified control instructions to the auxiliary material addition execution mechanism.

[0031] Specifically, the verified control instructions are the double verification results of digital twin preview and safety verification, ensuring the reliability and executability of the instructions. The auxiliary material addition actuator is a control terminal including a precision metering pump and a dynamic mixing device, which adjusts the auxiliary material ratio and injection rate according to the instructions.

[0032] The present invention constructs a multidimensional perception and control model based on a dynamic threshold system, and realizes active prediction and rapid response of production anomalies through hierarchical screening and pattern matching of real-time data streams. The system first establishes a dynamically adjusted threshold matrix, covering the core parameters of raw material characteristics, environmental conditions and finished product quality control, and then triggers intelligent switching of the three modes of routine, adjustment and exception handling through high-frequency data collection and comparison. Closed-loop control is formed between each mode through historical data backtracking, cross-batch parameter sharing and virtual simulation verification to ensure the accuracy of auxiliary material addition and process stability.

[0033] Alternatively, if Figure 2 As shown, the data analysis module includes: A deviation analysis unit, used to calculate the deviation of each indicator in the current production data relative to the dynamic threshold matrix; Specifically, the deviation analysis unit is a processing module that calculates the relative deviation between each indicator of the current production data and the corresponding benchmark value in the dynamic threshold matrix. The output value of the fluctuation degree of the quantitative indicator is the basic basis for subsequent mode judgment. The deviation adopts the percentage difference algorithm to eliminate the influence of inconsistent parameter dimensions.

[0034] An abnormality judgment unit, used to trigger the abnormality handling mode when it is detected that the deviation of at least one indicator exceeds a preset warning value; Specifically, the abnormality judgment unit is a logic controller that marks the abnormality level when the deviation of at least one indicator exceeds a preset warning value. The warning value is a mandatory intervention boundary comprehensively defined based on the equipment's extreme performance and finished product quality standards. Once triggered, the current production status is immediately locked and the safety protocol is started.

[0035] An adjustment judgment unit, configured to trigger the adjustment mode when the deviation of all indicators is within a preset adjustment interval; Specifically, the adjustment judgment unit is a parameter correction module that is activated when it detects that the deviation of all indicators is within a preset adjustment range. The adjustment range is a controllable fluctuation range obtained by process expert experience and statistical analysis of historical data, allowing the system to autonomously perform compensation operations without interrupting production.

[0036] The normal judgment unit is used to maintain the normal mode when the deviation of all indicators does not exceed the preset allowable fluctuation range.

[0037] Specifically, the conventional judgment unit is a steady-state controller that maintains a basic operating mode, and continuously calls standard recipe parameters when it detects that all indicators are within the allowable fluctuation range, and the allowable fluctuation range is a safety margin range of the equipment calibration accuracy.

[0038] For example, by building a multi-level deviation judgment system, dynamic mode precise scheduling is achieved, the strong intervention characteristics of the abnormal judgment unit are used to quickly isolate major risks, the predictive compensation of the adjustment judgment unit is relied on to maintain the steady-state transition of the process, and the baseline maintenance capability of the conventional judgment unit is used to optimize resource consumption. Its beneficial effect is to establish an intelligent decision-making chain with hierarchical response, realize progressive handling from minor parameter fluctuations to serious equipment abnormalities, improve the efficiency of quality risk interception while ensuring production continuity, avoid excessive intervention or delayed response problems in traditional control strategies through the priority scheduling mechanism between modes, and form a closed-loop optimization system that takes into account both production efficiency and safety control.

[0039] Optionally, the adjustment mode includes: Retrieve a set of historical parameters from historical production batches that match the current deviation; Specifically, the historical parameter set is a group of past production record data stored in the system database. Its sampling standard is the operating condition characteristics that match the current deviation threshold range. The matching process uses a dynamic time warping algorithm to align the time series differences between batches. The screened parameter set must meet the similarity requirements of the three-axis fluctuation trends of temperature, humidity and viscosity, and verify the correlation strength between historical data and current operating conditions through the Pearson correlation coefficient.

[0040] Calculating a dynamic compensation coefficient of the auxiliary material addition rate based on the historical parameter set; Specifically, the dynamic compensation coefficient is a dimensionless indicator that characterizes the adjustment range of the auxiliary material addition rate. Its calculation process uses the sliding window averaging method to process the additive placement records in the historical parameter set, and calculates the compensation weight value based on the real-time throughput of the current production line. Finally, the time response curve of the compensation coefficient is optimized through the fuzzy logic reasoning engine.

[0041] The dynamic compensation coefficient is added to the current recipe parameter to generate a corrected control parameter.

[0042] Specifically, the corrected control parameters are a new set of instructions that have been iteratively optimized. The generation process retains the baseline framework of the original recipe parameters and superimposes compensation coefficients to form composite control instructions. The superposition algorithm uses a half-life decay model to ensure a smooth transition between new and old parameters. The instruction queue uses a double buffering mechanism to avoid mechanical shocks to the production line caused by sudden parameter jumps.

[0043] For example, the intelligent matching and compensation calculation of historical working conditions can be used to predict production fluctuations, and refined dynamic adjustments can be made while maintaining the original formula framework, which can effectively balance the relationship between process stability and production flexibility. Its beneficial effect is to reduce the trial and error cost of the parameter setting process through historical data reuse, capture the short-term fluctuation characteristics of process parameters using sliding window technology, and improve the applicability of compensation coefficients by combining the reasoning ability of fuzzy logic engines. Finally, the control instructions can be switched without disturbance through a double buffer mechanism, which can improve the consistency of finished product quality while extending the service life of the equipment, forming an intelligent control paradigm that is driven by historical experience and coordinated with real-time data feedback.

[0044] Optionally, the dynamic compensation coefficient for calculating the auxiliary material addition rate includes: Establish a sliding time window, the length of which is 10% of the duration of the current production batch; Specifically, the sliding time window is a data collection period whose length is automatically adjusted according to the current production progress. The window length is set to 10% of the length of the current production batch to ensure that the sampling cycle is updated synchronously with the process rhythm. The sliding step size of the window is configured as the minimum time unit of the production rhythm to achieve continuous coverage of data fragments. The data in the window uses timestamp alignment technology to eliminate the time accumulation error of the production equipment.

[0045] Extracting the historical parameter change rate within the sliding time window and calculating the predicted compensation amount; Specifically, the historical parameter change rate is the fluctuation gradient indicator of the auxiliary material addition rate within the statistical window. The calculation process uses the least squares method to fit the parameter change trend line and quantify the change rate through differential operation. The predicted compensation amount generation method introduces an adaptive Kalman filter algorithm to reduce the noise of the original fluctuation data, and finally the theoretical compensation demand within the next three production cycles is deduced through the gray prediction model.

[0046] Among them, historical parameter matching uses the dynamic time warping algorithm (DTW) to calculate the similarity between historical batches and current data sequences. ,have , In the formula, The first data points, is the first data points. The historical parameters with similarity greater than 0.8 are included in the candidate set. Linear interpolation is performed on the historical batch data sequence, and the sampling frequency is unified to 1Hz; the maximum time expansion ratio allowed during matching is ±20%, and sequences beyond this range are considered unrelated.

[0047] The predicted compensation amount is weightedly fused with the conventional compensation amount to output a final dynamic compensation coefficient.

[0048] Specifically, the conventional compensation amount is the basic adjustment amount reference value generated according to the equipment calibration manual. Its weight distribution coefficient is dynamically adjusted through the real-time monitoring values ​​of the temperature and humidity in the production environment. The weighted fusion algorithm uses an improved entropy weight method to calculate the contribution of each compensation component. At the same time, the process optimization rules in the expert experience library are introduced to constrain the reasonable range of the fusion results, and finally a dynamic compensation coefficient that takes into account both prediction accuracy and operational stability is generated.

[0049] Among them, the weighted logic is the fusion weight of the conventional compensation amount and the predicted compensation amount ,have , In the formula, is the rate of change of ambient humidity, indicating the rate of change of the current ambient humidity, and is used to dynamically adjust the compensation strategy; For the final dynamic compensation coefficient ,have , In the formula, To predict the compensation amount, This is the normal compensation amount.

[0050] For example, the time characteristics of historical data are innovatively integrated into the compensation calculation process through the sliding window algorithm, the trend changes of process parameters are captured in the dynamic time dimension, and the advanced prediction model and robust weighting strategy are combined to achieve accurate prediction of the compensation amount. The beneficial effect is to break through the static limitations of traditional compensation methods, establish a synergistic mechanism of time-varying parameter analysis and adaptive weight adjustment, effectively reduce the regulation lag effect caused by equipment response delay, improve the predictability and flexibility of auxiliary material addition rate control, ensure the robust adaptability of product quality to fluctuations in the production environment, and form an intelligent compensation technology system with both timeliness and reliability.

[0051] Optionally, the exception handling mode includes: Extract the control parameters of the three processes preset for the current production batch; Specifically, the three preset processes are the control variable sets of the mixing temperature control process in the raw material pretreatment stage, the auxiliary material quantitative addition process and the semi-finished product forming process. The selection basis is the key quality control nodes determined by the process stability analysis. The parameter extraction range covers the real-time recorded values ​​of the equipment operating parameters and the process status mark values. The complete data sequence within the last two production cycles is obtained through the backtracking interface of the time series database.

[0052] Perform multi-dimensional feature matching on the control parameters and the historical fault case library; Specifically, the historical fault case library is a structured storage database of process abnormal events. Each case record contains fault characterization parameters, fault cause code and disposal plan index. The multi-dimensional feature matching uses an improved cosine similarity algorithm to compare the dimensional space distance between the current parameter feature vector and the case library feature matrix, and uses principal component analysis to reduce the dimension and optimize the efficiency and accuracy of similarity calculation.

[0053] Generate processing instructions containing device calibration priorities and recipe reset solutions based on the matching results.

[0054] Specifically, the equipment calibration priority is a sorted list generated according to the degree of fault impact and the urgency of repair. The sorting weight is dynamically determined by the product of the equipment downtime cost coefficient and the fault propagation risk value. The recipe reset scheme is an optimized ratio parameter set output by the adaptive strategy generation module based on the fault type. The generation process integrates expert experience rules and optimization suggestions output by the reinforcement learning model.

[0055] For example, the solution achieves efficient tracing and intelligent handling decisions of production anomalies, accurately locks in the root cause of the problem by focusing on multi-dimensional fault feature matching of key processes, and establishes a rapid fault mode identification mechanism combined with deep learning of historical cases. Its beneficial effects are to shorten the abnormal response time while improving the scientificity and reliability of the handling plan, optimize the allocation efficiency of maintenance resources through the calibration priority sorting mechanism, reduce quality losses in batch production with the help of the dynamic generation capability of the recipe reset plan, and form an intelligent optimization system for closed-loop fault management.

[0056] Optionally, performing multi-dimensional feature matching on the control parameter and the historical fault case library includes: Constructing a three-dimensional weight matrix of the current abnormal characteristics, wherein the three-dimensional weight matrix includes parameter deviation, equipment aging coefficient and environmental interference factor; Specifically, the three-dimensional weight matrix is ​​a three-dimensional evaluation model that integrates parameter deviation, equipment aging coefficient, and environmental interference factor. The parameter deviation is the percentage deviation between the real-time monitoring value and the standard threshold, the equipment aging coefficient is the performance attenuation index calculated based on the cumulative operating time and maintenance records of the equipment, and the environmental interference factor is the normalized value of the temperature, humidity, and air pressure data of the production workshop. The matrix construction process uses the hierarchical analysis method to determine the weight distribution ratio of each dimension and verifies the robustness of the model through orthogonal experiments.

[0057] Calculating feature similarity between the three-dimensional weight matrix and historical fault cases; Specifically, the feature similarity calculation uses an improved cosine similarity algorithm to quantify the matching score of the standardized matrix data. The improvement is that a double weight factor is applied to the parameter deviation dimension and Gaussian kernel function smoothing is performed on the environmental interference factor. In the data dimensionality reduction stage, the principal component analysis method is used to extract the top three principal component vectors of influence as the core indicator set for similarity calculation.

[0058] The parameter deviation is , where is the current parameter value, indicating the actual operating parameters of the device or system. It is a standard parameter value, which means the parameter value of the equipment or system during design or normal operation; The equipment aging factor is , where is the cumulative running hours, is the number of historical failures, , ;parameter , The equipment failure rate curve is obtained by fitting the Weibull distribution model. When the cumulative running time When it is greater than 2000 hours, the aging coefficient A increases exponentially.

[0059] The feature similarity is , where Environmental interference factors.

[0060] The processing strategy corresponding to the historical case with the highest feature similarity is selected as the basic template.

[0061] Specifically, the basic template is a standard disposal plan framework for selecting the best matching cases from the historical case library. The selection process introduces a dual optimization mechanism of case effectiveness index and disposal timeliness score. The disposal strategy generation stage combines the actual working conditions of the current production line to make priority adjustments and parameter fine-tuning on the basis of the template, and finally outputs a personalized disposal plan through a weighted decision tree.

[0062] For example, the equipment status environmental factors and process parameters are innovatively combined through the three-dimensional weight matrix, breaking through the limitations of single parameter comparison in traditional fault analysis, and using intelligent feature space matching algorithms to improve the accuracy of similar case retrieval and the adaptability of processing decisions. The beneficial effect is to establish a multi-dimensional feature fusion fault diagnosis system to achieve rapid analysis of complex abnormal scenarios, enhance the processing weights of key influencing factors through weight distribution optimization, and form a dynamically optimized disposal strategy library combined with the continuous learning ability of the case library, which significantly improves equipment maintenance efficiency and reduces the probability of secondary failures.

[0063] Optionally, sending the verified control instruction to the auxiliary material adding execution mechanism includes: Create a digital twin model of the excipient addition process; Specifically, the digital twin model is a virtual simulation environment that integrates the operating rules of the physical production line with real-time sensor data. Its modeling basis includes the three-dimensional structural topological data of the equipment, the dynamic parameters of the transmission system and the rheological characteristic curve of the material. It can synchronize the data with the physical production line in seconds through the industrial Internet of Things interface. The built-in physical engine of the model supports the precise simulation of the gradual change process of the auxiliary material mixing state.

[0064] Loading the control instructions and real-time environmental parameters into the digital twin model; Specifically, the real-time environmental parameters are a multi-dimensional data set of temperature, humidity, air pressure and light collected by distributed sensors in the workshop. The loading process uses a dynamic resource configuration algorithm to match the timestamps and spatial coordinate systems of the physical production line and the virtual model. The loading strategy of the control instructions injects simulation triggers in the order of the equipment response priority execution queue.

[0065] After the simulation runs, quality prediction indicators of the virtual finished product are obtained; Specifically, the quality prediction indicators of virtual finished products include the calculation results of physical and chemical parameters such as sugar content, uniformity, hardness value, and dissolution rate. The generation process simulates the formation process of the microstructure of sugar particles through the discrete element method and uses the finite element algorithm to calculate the macroscopic physical properties. The prediction indicators display the spatial distribution characteristics in the form of a heat map through a visual interface.

[0066] When the deviation between the quality prediction index and the preset standard is less than an allowable threshold, the control instruction is confirmed to be valid.

[0067] Specifically, the allowable threshold is a fluctuation tolerance range that is dynamically adjusted based on the product acceptance specifications. The deviation judgment uses a fuzzy logic algorithm to comprehensively evaluate the cumulative effects of multiple indicators. The confirmation process includes an automatic verification module based on an expert knowledge base across professional fields, which automatically triggers manual review requests for critical status cases.

[0068] For example, by reconstructing the digital mirror of the actual production line in the virtual space, the control strategy can be pre-verified, and a real-time mapping channel from the physical world to the digital space can be constructed. The beneficial effect is that potential production process defects can be exposed in advance through high-precision simulation, the cost of physical trial and error can be reduced through quantitative analysis of quality prediction indicators, and a multi-level safety verification mechanism for control instructions can be formed using intelligent threshold judgment technology. This can enhance the traceability of the quality control process while improving production safety, thus forming a closed-loop optimization control system that collaborates between the virtual and the real.

[0069] Optionally, the simulation operation includes: Align the timing labels of the actual production line with the digital twin model; Specifically, the timing label is a synchronization identifier that accurately marks the time point of equipment action. The alignment operation is achieved through the joint action of the hardware clock synchronization module and the software delay compensation algorithm. The network time protocol is used to calibrate the clock benchmark of the physical production line controller and the simulation server, and the interpolation algorithm is used to repair the time slot jitter offset in data transmission, ultimately ensuring that the operating rhythm of the virtual model is completely consistent with actual production.

[0070] Among them, the alignment timing tag realizes time synchronization through the Industrial Internet of Things OPC UA protocol; first, the physical device controller sends a timestamp every 200ms ; Then, the simulation server calculates the clock deviation , where It is the timestamp of the simulation server itself; when the clock deviation is greater than 10ms, the time interpolation correction is triggered.

[0071] Add random disturbance factors to simulate equipment execution errors; Specifically, the random disturbance factor is a virtual disturbance that simulates the equipment precision attenuation and mechanical wear. It is generated based on the fault probability distribution in the equipment's historical maintenance records. The disturbance amplitude is dynamically adjusted according to the servo mechanism positioning accuracy level. The injection method uses the Monte Carlo method to superimpose normally distributed random noise in the control instruction. At the same time, a nonlinear interference model is introduced to reproduce mechanical transmission characteristic deviations such as gear clearance.

[0072] Record the data fluctuation range of the simulation process and generate a safety verification report.

[0073] Specifically, the data fluctuation range is the maximum and minimum values ​​and standard deviation statistics of key parameters during the simulation operation. The recording process uses the sliding window analysis method to capture transient abnormal signals. The safety verification report includes the statistical curve of the equipment action exceeding the limit frequency and the parameter out-of-bounds heat map. The report generation module integrates the fuzzy comprehensive evaluation algorithm and the risk matrix template to automatically divide the risk level and generate a list of disposal recommendations.

[0074] Among them, the threshold setting rule for the deviation of the quality prediction index is: when the production batch is greater than 1000 pieces: max(0.5%, 0.1% of the total cost of raw materials); the Monte Carlo perturbation factor injection formula is: , where is a normally distributed random number.

[0075] For example, a digital twin test environment close to reality is built through high-precision timing calibration and controllable disturbance injection technology, and potential operational risks are deeply explored using multi-dimensional data analysis methods. The beneficial effect is that it breaks through the limitations of idealized assumptions in traditional simulation tests, improves the credibility and engineering practical value of test results by simulating real equipment errors, and provides accurate decision-making basis for process optimization in combination with an automated risk quantification assessment system, forming a complete digital verification closed loop covering test design execution and analysis, significantly enhancing the fault tolerance and safety protection level of the control system.

[0076] Optionally, the calculation of the predicted compensation amount includes: Get the ambient temperature and humidity change trend for the next 15 minutes; Specifically, the changing trend of ambient temperature and humidity is the short-term climate change data predicted by the fusion of the workshop's external meteorological station and the indoor microenvironment sensor. The prediction algorithm uses the time series decomposition method to separate the seasonal and random components and then uses the ARIMA model to deduce the future change curve. The data collection cycle is set to update every 30 seconds to capture the transient characteristics of rapid disturbances.

[0077] Long short-term memory neural network is used to predict changes in auxiliary material demand; Specifically, the long short-term memory neural network is a deep time series prediction model equipped with a forget gate and a memory gate structure. Its input features include the temperature and humidity correlation factors of the historical consumption rate of auxiliary materials and the equipment operation status encoding. The attention mechanism is introduced into the model training process to strengthen the feature learning of key time nodes. The prediction results are decomposed into a dual-channel output of the demand trend component and the periodic fluctuation component.

[0078] The structure of the long short-term memory neural network can be that the input layer is 6 nodes, the temperature, humidity, and viscosity historical values; the double-layer LSTM has 64 units per layer. The training data is 50,000 sets of production records containing different seasons / raw material batches. The loss function is SmoothL1Loss, the learning rate is 0.001, that is, the Adam optimizer. The input feature normalization adopts the RobustScaler method.

[0079] The length and weight distribution of the sliding time window are modified based on the prediction results.

[0080] Specifically, the sliding window length correction algorithm dynamically adjusts the data capture range according to the gradient change of the auxiliary material demand trend component, shortens the window in the steep rise stage to enhance sensitivity, and lengthens the window in the stable stage to improve stability. The weight distribution update assigns differentiated time attenuation factors to historical data based on the amplitude characteristics of the periodic fluctuation component, and optimizes the weight distribution ratio through the matrix confusion algorithm.

[0081] For example, a refined auxiliary material demand prediction mechanism is established by integrating meteorological forecasting technology with deep time series models, and the intelligent adaptation of the data analysis model is realized by combining the dynamic self-adjustment strategy of sliding window parameters. The beneficial effect is to break through the applicability limitations of traditional fixed window analysis modes to dynamic process scenarios, and use the nonlinear mapping capability of neural networks to accurately capture the coupling relationship between complex environmental variables and auxiliary material demand. The sensitivity and stability of the prediction model are effectively balanced through real-time optimization of window parameters, forming an intelligent control system with strong climate adaptability, which significantly enhances the production system's ability to actively adjust to environmental fluctuations.

[0082] Embodiment 1: In order to verify the implementation effect of the present invention, the present invention is applied to a throat lozenge production line under a food group. The production line mainly produces functional throat lozenges containing herbal extracts, and the addition ratio of auxiliary materials such as honey, menthol and Chinese herbal medicine extracts needs to be accurately controlled. The traditional production method relies on manual experience to adjust parameters and cannot respond to raw material fluctuations and environmental changes in real time, resulting in problems such as uneven sugar content of the finished product and deviation in the content of effective ingredients.

[0083] In this embodiment, a dynamic threshold matrix is ​​constructed through a threshold matrix establishment module, and the viscosity reference value is set to 4500cP (25°C), the sugar content floating range is ±2%, and the temperature and humidity critical points are 25°C ±3°C and 45%RH ±5%. The data acquisition module integrates a high-precision viscosity sensor, an infrared sugar meter, and a temperature and humidity detector to collect the viscosity parameters of the raw material mixing tank, the environmental data of the auxiliary material bin, and the sugar content of the finished product in the molding section in real time.

[0084] When the ambient temperature is detected to rise suddenly to 28°C (5% above the baseline threshold), the data analysis module triggers the adjustment mode. First, historical parameter matching is performed, and historical data of similar temperature rise scenarios in the past 30 batches are retrieved to screen out the 5 groups of samples with the highest auxiliary material compensation. Then, dynamic compensation calculation is performed based on the sliding window algorithm, with the window length being 10% of the current batch production time. The increment of the honey addition rate is calculated, and the temperature rise trend in the next 15 minutes is predicted. The LSTM network is used to predict, thereby generating a compensation coefficient of 0.15. Then, instruction pre-verification is performed, and the corrected instructions are loaded in the digital twin model. The simulation operation shows that the sugar content fluctuation of the finished product has dropped from ±3% to ±1.2%, confirming the effectiveness of the instruction. Finally, smooth switching execution is performed, and the control execution module adopts a gradual transition strategy, in which the inertia compensation factor is 0.8, and the metering pump rate is gradually adjusted within 10 seconds to avoid mechanical shock.

[0085] Two production lines with the same production capacity were selected for comparison. The experimental group applied the present invention, and the control group used traditional PID control. 100 batches were produced continuously, each batch lasting 2 hours. The experimental group and the control group used the same raw materials, and the key indicators monitored included: the qualified rate of finished sugar content, with a target value of 75%-80%; the metering error of auxiliary material addition, less than or equal to ±1.5%; and the abnormal response time, which is the time from detecting the parameter crossing the limit to executing the adjustment.

[0086] The data showed that the sugar content qualified rate of the experimental group's finished products reached 98.3%, while that of the control group was 84.7%. In the afternoon when the ambient temperature fluctuated frequently, the experimental group compensated autonomously 26 times through the adjustment mode, and the sugar content standard deviation was 0.8%, which was significantly lower than the 2.1% of the control group; when the viscosity sensor detected that the viscosity of the raw material deviated by 8%, the experimental group triggered the quality backtracking mode, located the problem of excessive mixing temperature in the previous process within 10 seconds, generated equipment calibration instructions, and the abnormal response time was 45 seconds; the control group relied on manual investigation, which took an average of 15 minutes. The average waste rate of auxiliary materials in the experimental group was reduced to 0.7%, a 72% reduction from the 2.4% of the control group.

[0087] Table 1 Comparison of blood pressure fluctuation data in patients with hypertension index Experimental Group Control group Sugar content qualified rate 98.3% 84.7% Measurement error (standard deviation) 0.9% 2.3% Abnormal response time ≤60 seconds 8-20 minutes Excipient waste rate 0.7% 2.4% From the data in Table 1 above, it can be seen that the control system of the present invention significantly improves the quality control accuracy of throat lozenge production through the dynamic threshold matrix and multi-mode coordination mechanism, and realizes the automation of the entire process from real-time monitoring, intelligent decision-making to closed-loop verification. Compared with traditional methods, it has obvious advantages in adaptability and abnormal response efficiency under complex working conditions, effectively reduces raw material loss and ensures product consistency, and meets the stringent production requirements of functional foods.

[0088] Based on the same inventive concept, Figure 3 As shown, the present invention also provides a method for controlling the addition of auxiliary materials in the production of throat lozenges, the method comprising: Constructing a dynamic threshold matrix, wherein the dynamic threshold matrix includes a viscosity reference value, a sugar content floating range, and an interval range of a temperature and humidity critical point; Collect current production data, including viscosity sensor measurement values ​​of the raw material conveying section, temperature and humidity monitoring data of the auxiliary material bin, and online detection indicators of finished products; generating a mode selection signal according to a comparison result between the current production data and the dynamic threshold matrix; activating a corresponding control mode based on the mode selection signal, the control mode including a normal mode, an adjustment mode and an abnormality handling mode; Execute the control instructions corresponding to the control mode, and send the verified control instructions to the auxiliary material adding execution mechanism.

[0089] It should be noted that the electrical connection between the above-mentioned units does not necessarily mean direct connection of the lines, and the indirect connection mode can be applied to the embodiments of the present invention as long as the purpose of the present invention is achieved. The above is only an exemplary embodiment of the present invention and cannot be used to limit the scope of the present invention.

[0090] That is, any equivalent changes and modifications made according to the teachings of the present invention are still within the scope of the present invention. After considering the disclosure of the specification and the truth of practice, those skilled in the art will easily think of other embodiments of the present invention. This application is intended to cover any variation, use or adaptive change of the present invention, which follows the general principles of the present invention and includes common knowledge or customary technical means in the art that are not described in the present invention.

Claims

1. A control system for adding auxiliary materials to throat lozenge production, characterized in that: The system comprises: A threshold matrix building module is used to build a dynamic threshold matrix, wherein the dynamic threshold matrix includes a viscosity reference value, a sugar content floating range, and an interval range of temperature and humidity critical points; A data acquisition module is used to collect current production data, including viscosity sensor measurement values ​​of the raw material conveying section, temperature and humidity monitoring data of the auxiliary material bin, and online detection indicators of finished products; A data analysis module, configured to generate a mode selection signal according to a comparison result between the current production data and the dynamic threshold matrix; A mode selection module, configured to activate a corresponding control mode based on the mode selection signal, wherein the control mode includes a normal mode, an adjustment mode, and an abnormality handling mode; The control execution module is used to execute the control instructions corresponding to the control mode and send the verified control instructions to the auxiliary material addition execution mechanism.

2. A control system for adding auxiliary materials to throat lozenge production according to claim 1, characterized in that: The data analysis module includes: A deviation analysis unit, used to calculate the deviation of each indicator in the current production data relative to the dynamic threshold matrix; An abnormality judgment unit, used to trigger the abnormality handling mode when it is detected that the deviation of at least one indicator exceeds a preset warning value; An adjustment judgment unit, configured to trigger the adjustment mode when the deviation of all indicators is within a preset adjustment interval; The normal judgment unit is used to maintain the normal mode when the deviation of all indicators does not exceed the preset allowable fluctuation range.

3. A control system for adding auxiliary materials to throat lozenge production according to claim 2, characterized in that: The adjustment modes include: Retrieve a set of historical parameters from historical production batches that match the current deviation; Calculating a dynamic compensation coefficient of the auxiliary material addition rate based on the historical parameter set; The dynamic compensation coefficient is added to the current recipe parameter to generate a corrected control parameter.

4. A control system for adding auxiliary materials to throat lozenge production according to claim 3, characterized in that: The dynamic compensation coefficient for calculating the auxiliary material addition rate includes: Establish a sliding time window, the length of which is 10% of the duration of the current production batch; Extracting the historical parameter change rate within the sliding time window and calculating the predicted compensation amount; The predicted compensation amount is weightedly fused with the conventional compensation amount to output a final dynamic compensation coefficient.

5. A control system for adding auxiliary materials to throat lozenge production according to claim 2, characterized in that: The exception handling modes include: Extract the control parameters of the three processes preset for the current production batch; Perform multi-dimensional feature matching on the control parameters and the historical fault case library; Generate processing instructions containing device calibration priorities and recipe reset solutions based on the matching results.

6. A control system for adding auxiliary materials to throat lozenge production according to claim 5, characterized in that: The multi-dimensional feature matching of the control parameters with the historical fault case library includes: Constructing a three-dimensional weight matrix of the current abnormal characteristics, wherein the three-dimensional weight matrix includes parameter deviation, equipment aging coefficient and environmental interference factor; Calculating feature similarity between the three-dimensional weight matrix and historical fault cases; The processing strategy corresponding to the historical case with the highest feature similarity is selected as the basic template.

7. A control system for adding auxiliary materials to throat lozenge production according to claim 1, characterized in that: The step of sending the verified control instruction to the auxiliary material adding actuator comprises: Create a digital twin model of the excipient addition process; Loading the control instructions and real-time environmental parameters into the digital twin model; After the simulation runs, quality prediction indicators of the virtual finished product are obtained; When the deviation between the quality prediction index and the preset standard is less than an allowable threshold, the control instruction is confirmed to be valid.

8. A control system for adding auxiliary materials to throat lozenge production according to claim 7, characterized in that: The simulation operation includes: Align the timing labels of the actual production line with the digital twin model; Add random disturbance factors to simulate equipment execution errors; Record the data fluctuation range of the simulation process and generate a safety verification report.

9. A control system for adding auxiliary materials to throat lozenge production according to claim 4, characterized in that: The calculation of the predicted compensation amount includes: Get the ambient temperature and humidity change trend for the next 15 minutes; Long short-term memory neural network is used to predict changes in auxiliary material demand; The length and weight distribution of the sliding time window are modified based on the prediction results.

10. A method for controlling the addition of auxiliary materials in the production of throat lozenges, using a control system for adding auxiliary materials in the production of throat lozenges as claimed in any one of claims 1 to 9, characterized in that: The method comprises: Constructing a dynamic threshold matrix, wherein the dynamic threshold matrix includes a viscosity reference value, a sugar content floating range, and an interval range of a temperature and humidity critical point; Collect current production data, including viscosity sensor measurement values ​​of the raw material conveying section, temperature and humidity monitoring data of the auxiliary material bin, and online detection indicators of finished products; generating a mode selection signal according to a comparison result between the current production data and the dynamic threshold matrix; activating a corresponding control mode based on the mode selection signal, the control mode including a normal mode, an adjustment mode and an abnormality handling mode; Execute the control instructions corresponding to the control mode, and send the verified control instructions to the auxiliary material adding execution mechanism.

Images