Intelligent pressure increasing and reducing control system of homogenizer based on servo synchronous transmission

Abstract

The invention relates to the field of homogenizer intelligence, and discloses a homogenizer intelligent pressure increasing and reducing control system based on servo synchronous transmission, which comprises the following steps: extracting the operation inertia difference of each plunger mechanism under a multi-pump parallel structure, generating a synchronous offset vector map, and calculating the pressure increasing and reducing of the homogenizer based on the synchronous offset vector map. Calling a slip registration algorithm and an inertia field decoupling network, extracting reconstructed plunger stroke and pressure response mapping data, constructing a three-dimensional flow-path-stress tensor model, judging whether fluctuation-wear coupling sensitive points exist or not, activating a frequency conversion regulation and control strategy set of a servo driving layer based on a disturbance window and the coupling sensitive points, and carrying out the control of the servo driving layer. And judging whether structural thermal drift feedback unbalance exists or not, dynamically adjusting servo redundancy and a buffer response strategy in combination with a preset life curve and an abnormal response backtracking channel, and outputting a synchronous regulation and control instruction set. The method has the advantage of improving the long-term operation reliability of the homogenizer.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of homogenizer intelligence, in particular to a homogenizer intelligent pressure increasing and decreasing control system based on servo synchronous transmission. BACKGROUND

[0002] As a device commonly used for liquid material micro-fining, the homogenizer has a wide application in food, cosmetics, biopharmaceuticals and fine chemical industries. Its working principle mainly relies on the high-pressure pump to extrude the material through the homogenizing valve to achieve the refinement and uniform distribution of the material particle size. With the increasing requirements of stability and precision in production, more and more homogenizing devices adopt servo motor synchronous transmission structure to improve the control performance and response speed of the device. However, in actual production, especially in large-scale homogenizing systems with multiple pumps in parallel, due to the inconsistent load response between servo motors, synchronization deviation is prone to occur, resulting in slight beat inconsistency during the operation of the plunger pump. Although this slight synchronization error does not immediately trigger a system alarm, it can cause uneven local mechanical wear after a long time of operation, leading to increased device vibration, higher maintenance frequency, and even shorter service life of key components such as plungers and sealing rings. For example, in a large beverage filling plant using a homogenizer with double plunger pumps, even if the parameters of the servo drives are consistent and accurate, the technical personnel still find that there is a microsecond-level time difference between the working strokes of the two plungers during continuous operation, resulting in increased output flow pulsation amplitude, uneven sealing component wear, and difficulty in unifying the maintenance cycle. As can be seen, although the existing technology has introduced a servo synchronization control architecture, there is still a certain technical gap between mechanical synchronization precision and long-term operation reliability. Therefore, it is necessary to design a homogenizer intelligent pressure increasing and decreasing control system based on servo synchronous transmission to improve the long-term operation reliability of the homogenizer. SUMMARY

[0003] In view of the deficiencies of the prior art, the present application provides a homogenizer intelligent pressure increasing and decreasing control system based on servo synchronous transmission, which has the advantage of improving the long-term operation reliability of the homogenizer and solves the problems in the above background technology.

[0004] To achieve the above purpose of improving the long-term operation reliability of the homogenizer, the present application provides the following technical solution: a homogenizer intelligent pressure increasing and decreasing control system based on servo synchronous transmission, comprising: A linkage identification module: through the high-frequency feedback data of the multi-axis servo execution unit, the running inertia difference of each plunger mechanism under the multi-pump parallel structure is extracted, the beat phase drift and real-time load micro-variation information are combined, a synchronization offset vector atlas is generated, and it is judged whether to trigger the pressure increasing and decreasing intervention logic. If yes, enter the beat reconstruction module. The beat reconstruction module: Based on the synchronous offset vector map spectrum, it calls the sliding registration algorithm and the inertial field decoupling network to perform deep fitting and repair of the beat micro-skew in the piston reciprocating path. At the same time, it integrates the thermal stability threshold curve to calculate the correction intensity factor and determine whether there is a linkage abnormal coupling. If so, it enters the flow disturbance identification module. Flow identification module: Extracts the reconstructed plunger stroke and pressure response mapping data, constructs a three-dimensional flow-path-stress tensor model, and uses a pulse flow mutation identification algorithm to calibrate the instantaneous disturbance window during the pressure increase and decrease process, and determines whether there are fluctuation-wear coupling sensitive points. If so, it enters the dynamic frequency conversion control module. Dynamic control module: Based on the disturbance window and coupling sensitive point, activate the frequency conversion control strategy set of the servo drive layer, integrate thermal inertia parameters to make dynamic power constraint judgment, and determine whether there is structural thermal drift feedback imbalance. If so, enter the adaptive synchronization optimization module. Synchronization optimization module: Combining preset lifespan curves and abnormal response backtracking channels, it dynamically adjusts servo redundancy and buffer response strategies, and outputs a set of synchronization control commands.

[0005] Preferably, the process for determining whether to trigger the stress-reduction intervention logic is as follows: By periodically collecting the cycle synchronization, piston stroke difference, and pressure change rate from the multi-axis servo feedback, an inertial offset mapping matrix for the current working cycle is constructed. The matrix is ​​compared with the system's preset dynamic threshold model. If the beat offset exceeds the threshold range or the inertial response changes abruptly, it is determined to be a synchronization imbalance event. When a synchronous imbalance event is detected, the response phase difference between pump groups and the load distribution trend are further analyzed. If the response phase difference is in a continuous divergent state, the pressure increase / decrease intervention logic is triggered, and the cycle reconfiguration process is initiated.

[0006] Preferably, the process of calling the sliding registration algorithm and the inertial field decoupling network is as follows: By deconstructing the real-time motion trajectory of the plunger system, a set of sliding path vectors for multiple time periods is constructed. An inertial coupling identification submodule is introduced to map the path vector set to the inertia tensor domain and separate the inertial coupling factors related to internal friction and hydraulic feedback of the structure. A sliding registration algorithm is used to perform similarity regression on the path offset of adjacent cycles, identify abnormal sliding points, and activate the inertial field decoupling network.

[0007] Preferably, the deep fitting and repair process for the micro-skewness of the piston's reciprocating path is as follows: High-frequency variation samples of piston stroke under multiple cycles are extracted to construct a fitting benchmark set for cycle drift; By integrating the thermal deformation coefficient of the plunger structure with the hydraulic hysteresis model, the sample data are subjected to time-domain alignment and offset factor normalization. Based on the weighted minimum residual fitting method, the beat correction value for each cycle is dynamically calculated to generate a fitting compensation vector.

[0008] Preferably, the determination of whether an abnormal coupling process constitutes a linkage is as follows: The repaired beat data is input into the linkage analysis model to calculate the response correlation matrix between each servo axis. Determine whether the correlation is trending towards an unbalanced state. If the decrease in multi-axis correlation exceeds the preset coupling threshold, it is determined that there is a phenomenon of linkage coupling attenuation. By combining the thermal stability threshold curve and the current load balancing status, a linkage anomaly scoring index is constructed. If the scoring index exceeds the coupling tolerance range, it is identified as linkage anomaly coupling.

[0009] Preferably, the process of constructing a three-dimensional flow-path-stress tensor model is as follows: The system collects real-time output flow data from the servo unit, the piston stroke fine-tuning trajectory, and the stress response curve from the hydraulic system. By integrating time-series information from three dimensions—flow, path, and stress—using tensor data structures, a dynamic tensor mapping field is constructed. Local perturbation enhancement processing is applied to the tensor mapping field to identify flow abrupt change points and stress overload regions.

[0010] Preferably, the process for determining whether a fluctuation-wear coupling sensitive point exists is as follows: Cross-filtering of abnormal flow paths and stress concentration areas in the tensor model to extract the mapping region set of potential wear areas; Analyze the coupling relationship between the flow rate change rate and path stability. If the coupling factor shows periodic amplification in a specific path segment, it is identified as a wear-sensitive point. By further combining historical wear trends with the current thermal drift status, it can be confirmed whether it belongs to a fluctuation-wear coupling area with linkage risk. If so, the frequency conversion control mechanism is triggered.

[0011] Preferably, the determination of whether a structural thermal drift feedback imbalance process exists is as follows: Collect the temperature distribution map of the multi-pump unit structure and the servo response hysteresis parameters to form the thermal feedback matrix for the current cycle; By combining historical thermal response curves and temperature rise trend models, the development path of thermal drift is predicted and its impact on system regulation delay is analyzed. If the servo control response and the thermal drift curve show an inverse correlation trend, and the offset time window continuously exceeds the set feedback tolerance, it is determined to be a thermal drift feedback imbalance.

[0012] Preferably, the process of outputting the set of synchronization control instructions is as follows: By comprehensively analyzing the servo redundancy configuration, buffer adjustment strategy, and thermal stability adaptation parameters output by the adaptive optimization module, a multi-axis coordinated drive scheme is generated. Based on the coordinated drive scheme, the waveform diagram of the pressure increase and decrease rhythm is extracted, and the pulse servo command sequence is adjusted according to the piston stroke compensation requirements to form the final set of synchronous control commands.

[0013] Compared with the prior art, the present invention provides an intelligent boosting and depressurization control system for a homogenizer based on servo synchronous transmission, which has the following beneficial effects: This invention utilizes a linkage identification module to precisely analyze high-frequency feedback data from multi-axis servo units, monitoring and capturing potential synchronization offsets and minor load variations in the system in real time, ensuring high coordination among the various plunger mechanisms. Upon detecting a potential synchronization imbalance, the system automatically triggers pressure-increasing intervention logic and employs a slip registration algorithm via a cycle time reconstruction module to deeply repair minor deviations in the plunger reciprocating path, ensuring the system remains in optimal operating condition. When flow disturbances or wear-sensitive points are detected, the flow identification module, through the construction of a three-dimensional flow-path-stress tensor model, further precisely calibrates instantaneous disturbances during pressure-increasing and depressurization processes, identifies potential fluctuation-wear coupling problems, and adjusts the operating state promptly to prevent excessive equipment wear. The dynamic control module, combining real-time disturbance windows and thermal inertia parameters, flexibly adjusts the frequency conversion control strategy of the servo drive system, effectively reducing feedback imbalances caused by thermal drift and ensuring stable operation of the equipment under high load conditions. The synchronization optimization module, by dynamically adjusting servo redundancy and buffer response strategies, combined with the system's lifespan curve and abnormal response backtracking, outputs a precise set of synchronization control commands, further improving equipment efficiency and lifespan. Through a sophisticated real-time feedback and dynamic adjustment mechanism, the system's operational stability has been improved, the equipment's service life has been effectively extended, maintenance costs have been reduced, and an efficient, intelligent, and sustainable production process has been achieved. Attached Figure Description

[0014] Figure 1 This is a schematic diagram of the structure of the present invention. Detailed Implementation

[0015] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0016] Example 1: Please refer to Figure 1As shown in the embodiment of the present invention, an intelligent boosting and depressurization control system for a homogenizer based on servo synchronous transmission includes: Linkage Identification Module: Through the high-frequency feedback data of the multi-axis servo actuator, the inertial difference of each plunger mechanism in the multi-pump parallel structure is extracted. Combined with the cycle phase drift and real-time load micro-change information, a synchronous offset vector map spectrum is generated, and it is determined whether the pressure increase and decrease intervention logic is triggered. If so, the cycle reconstruction module is entered. The process for determining whether the pressure increase / depression intervention logic is triggered in the linkage identification module is as follows: By periodically collecting the cycle synchronization, plunger stroke difference, and pressure change rate from the multi-axis servo feedback, an inertial offset mapping matrix for the current working cycle is constructed. The system automatically collects servo axis feedback data in each servo working cycle, extracts the timing response characteristics and actual stroke execution trajectory of each axis within a unit cycle, and monitors the pressure change curve synchronized with it. The plunger motion deviation, cycle rhythm drift, and pressure gradient change rate are uniformly mapped into an inertial response feature matrix, forming an inertial offset mapping matrix that reflects the dynamic coupling relationship between each pump group. The matrix is ​​compared with the system's preset dynamic threshold model. If the cycle offset exceeds the threshold range or the inertial response changes abruptly, it is determined to be a synchronization imbalance event. The system internally stores a dynamic threshold model that matches the equipment model and operating parameters, including parameters such as cycle drift limit, stroke error bandwidth, and pressure fluctuation tolerance band. The inertial offset matrix of the current working cycle is compared with the matrix to evaluate whether the cycle synchronization offset exceeds the allowable range or whether the piston response inertia changes abruptly. If any item is found to exceed the threshold model setting range, it is determined that a synchronization imbalance event has occurred in the current cycle. When a synchronization imbalance event is detected, the response phase difference and load distribution trend between pump groups are further analyzed. If the response phase difference is in a state of continuous divergence, the pressure increase / depression intervention logic is triggered, and the cycle reconfiguration process is initiated. Combining the phase difference and load trend data, the system calculates whether it has entered a "continuously divergent response phase state" as the triggering basis for the intervention logic. When the phase difference continues to widen and the load offset fails to return to equilibrium within the expected period, the system determines that there is a risk of continuous divergence, which means that the synchronization coordination mechanism between multiple pump groups has failed or is on the verge of failure. When the system is determined to have entered a state of continuous divergence in response phase, and the duration of this state exceeds the minimum response tolerance period set by the system, the pressure increase / depression intervention logic is triggered, and the cycle reconfiguration process is initiated simultaneously. The pressure increase / depression intervention logic includes adjusting the target values ​​of the hydraulic main circuit and branch pressure, correcting the buffer pressure control parameters, and redistributing the load execution path to achieve rapid recovery of the system's dynamic response capability. At the same time as triggering the intervention, the system will automatically start the cycle reconfiguration process to refit and optimize the current cycle parameters to ensure the recovery and stable operation of the multi-axis coordinated rhythm.

[0017] The beat reconstruction module: Based on the synchronous offset vector map spectrum, it calls the sliding registration algorithm and the inertial field decoupling network to perform deep fitting and repair of the beat micro-skew in the piston reciprocating path. At the same time, it integrates the thermal stability threshold curve to calculate the correction intensity factor and determine whether there is a linkage abnormal coupling. If so, it enters the flow disturbance identification module. The process of calling the sliding registration algorithm and the inertial field decoupling network in the beat reconstruction module is as follows: By deconstructing the real-time motion trajectory of the plunger system, a multi-time-period slip path vector set is constructed. The system first records the plunger's displacement-time curve in each working cycle by high-speed sampling of servo feedback data. Temporal resampling and B-spline interpolation methods are used to smooth the displacement curves and eliminate local high-frequency noise. Based on the first and second derivatives of the displacement, the complete motion trajectory vector of the plunger is extracted, including the starting point, constant velocity segment, reversal point, and braking point. The motion trajectories of multiple consecutive cycles are constructed into a slip path vector set, which is a trajectory curve for one cycle, used to characterize the non-ideal slip behavior of the plunger at a microscale. A standard path is established with the plunger's theoretical cycle model as a reference to achieve offset measurement. An inertial coupling identification submodule is introduced to map the path vector set to the inertia tensor domain, separating the inertial coupling factors related to internal structural friction and hydraulic feedback. After the path vector set is constructed, the inertial coupling identification submodule is called to perform tensor processing on the trajectory data: a high-order inertial descriptor is constructed using the velocity change rate, response delay, and inertial response curvature of each path vector, forming an inertial feature tensor set. This set is then mapped to the inertia tensor domain, and the main inertial coupling factors are separated through principal component analysis or independent component analysis, including: local inertial coupling caused by structural friction; inertial anomalies caused by hydraulic backflow or back pressure disturbance; and system-level inertial inconsistencies caused by assembly errors or mass asymmetry.

[0018] A sliding registration algorithm is used to perform similarity regression on the offset of adjacent cycle paths, identify abnormal sliding points, and activate the inertial field decoupling network. Based on the set of sliding paths, the sliding registration algorithm is executed to detect and quantify the relative offset behavior of the plunger beat in continuous cycles: a registration loss function is constructed: a path registration similarity metric function is defined to calculate the path shape difference; sliding registration window matching: for any two continuous paths, a rigid / non-rigid registration model is applied to minimize the path registration error, while recording the sliding displacement vector; regressing abnormal points: if multiple consecutive points show a sudden increase in offset, local breakage, or a sharp decrease in similarity, an abnormal sliding event is determined, and the location of the abnormal point and the affected path segment are recorded. The registration results are used to assist in locating time segments where fundamental problems such as system-level misalignment, feedback anomalies, or control drift exist during piston operation. The inertial field decoupling network is activated to correct and compensate for slip coupling disturbances. After abnormal slip points are identified during the slip registration stage, the system automatically activates the inertial field decoupling network module: the path offset vector and the corresponding inertial factor tensor are input into the decoupling network; the network uses a multi-layer graph neural network or residual convolutional network as its core structure to construct a nonlinear mapping relationship between the slip trajectory and the inertial factor; the network learns the coupling weights of slip offset and various inertial coupling factors through supervised learning training; the output is a set of correction vectors, which can be used to compensate for control commands within the current cycle to counteract the response error caused by inertial slip; the feedforward path injected into the piston controller dynamically adjusts the target position and velocity profile curves to ensure high-precision closed-loop alignment between the actual trajectory and the theoretical trajectory.

[0019] The deep fitting and repair process for the micro-skewness of the piston reciprocating path in the beat reconstruction module is as follows: High-frequency variation samples of the plunger stroke under multiple cycles are extracted to construct a fitting benchmark set for cycle drift. The system first performs high-frequency sampling of the plunger displacement feedback data in multiple working cycles of continuous operation, recording the complete path of each reciprocating motion. Using the sliding window technique, the high-frequency variation region in the plunger stroke is extracted in each cycle, with particular attention paid to the trajectory disturbance features near the reversing point, braking point, and starting point, forming a micro-skew sample set. The path segments in each cycle are uniformly converted to a relative time scale, and the stable intervals in the motion cycle are removed, retaining only the disturbance segments that have identification value for cycle drift, forming a fitting benchmark set for cycle drift. By integrating the thermal deformation coefficient of the plunger structure with the hydraulic hysteresis model, the sample data is time-domain aligned and the offset factor is normalized. A thermo-hydraulic joint influence factor matrix is ​​established by introducing the material thermal expansion coefficient of the plunger assembly and the hydraulic channel delay response model. This matrix is ​​used to correct each trajectory in the sample set to eliminate structural time drift caused by thermal deformation or hydraulic hysteresis. The trajectory curves of multiple cycles are aligned in the time domain using a dynamic time warping algorithm to ensure that the micro-skew features are expressed under a unified reference time axis. All sample data are normalized to uniformly map the micro-skew offset values ​​to the standard reference scale range to adapt to the weight balance in the subsequent fitting process. Based on the weighted minimum residual fitting method, the cycle correction value for each period is dynamically calculated to generate a fitting compensation vector. The weighted minimum residual fitting algorithm is used to perform dynamic trajectory regression on the normalized sample set. A residual weight matrix is ​​set for the key skew segment, and higher fitting weights are assigned to the commutation disturbance region to improve the algorithm's response sensitivity to critical cycle drift. During the fitting process, the cycle correction value for each period is dynamically adjusted, and the fitting compensation vector is generated accordingly. The fitting compensation vector serves as the correction input for the cycle synchronization controller in the control system, used to update the piston cycle scheduling parameters and complete the real-time repair of micro-skew.

[0020] The process for determining whether abnormal coupling occurs in the beat reconstruction module is as follows: The repaired beat data is input into the linkage analysis model to calculate the response correlation matrix between each servo axis. The system first calls the beat repair data output by the beat reconstruction module to extract the synchronous response characteristics of each servo axis in each cycle. The timing data of each axis is sent into the multivariate response coupling analysis model to generate a periodic response correlation matrix. Each element of this matrix represents the response coupling strength between axes in the current beat cycle, which is used to identify the linkage change trend within the servo system. To determine if the correlation is becoming unbalanced, if the decrease in multi-axis correlation exceeds a preset coupling threshold, it is determined that there is a linkage coupling attenuation phenomenon; continuously track the response correlation matrix for multiple cycles and calculate the coupling decrease ratio matrix between adjacent cycles; perform differential analysis on the elements to identify servo axis pairs whose decrease exceeds the system's set coupling threshold; if there are multiple servo axis pairs and they appear continuously in consecutive cycles, it is determined that the system has a "linkage coupling attenuation" phenomenon; Combining the thermal stability threshold curve and the current load balancing status, a linkage anomaly scoring index is constructed. If the scoring index exceeds the coupling tolerance range, it is considered an abnormal linkage coupling. The system calculates the thermal stability index for the current cycle based on the spindle temperature field data collected by sensors and the internal thermal drift data of the servo motor. If the thermal stability index is within a reasonable fluctuation range, it indicates that the coupling change in this cycle is not caused by temperature rise, eliminating the dominant role of temperature in the linkage effect of the servo system. The system monitors the load distribution and hydraulic feedback pressure differences in real time and calculates the load balance index to determine whether the load offset has caused the decoupling or coupling degradation of the servo axis. If the load balance index shows that the load distribution is within a reasonable range, it further confirms that the coupling change in this cycle is unrelated to the load. The system comprehensively considers the above two factors to construct the linkage anomaly scoring index. During the calculation process, the system evaluates the response change amplitude between each servo axis pair and makes appropriate weighted adjustments based on the thermal stability and load balance status. If the scoring index exceeds the set coupling tolerance threshold, the current cycle is determined to be an abnormal coupling event. Once the scoring index exceeds the set tolerance threshold, the system will automatically record the identifier code and timestamp of the abnormal event, providing necessary evidence for subsequent intervention logic or alarm modules. At this time, the system can further trigger intervention mechanisms, such as adjusting the pressure distribution of each axis or initiating cycle reconfiguration, to restore the system to its normal linkage state.

[0021] Flow identification module: Extracts the reconstructed plunger stroke and pressure response mapping data, constructs a three-dimensional flow-path-stress tensor model, and uses a pulse flow mutation identification algorithm to calibrate the instantaneous disturbance window during the pressure increase and decrease process, and determines whether there are fluctuation-wear coupling sensitive points. If so, it enters the dynamic frequency conversion control module. The process of constructing the three-dimensional flow-path-stress tensor model in the flow identification module is as follows: The system collects real-time output flow data from the servo unit, the fine-tuning trajectory of the piston stroke, and the stress response curve from the hydraulic system. First, a high-speed sensor system periodically collects flow data from the servo unit, the fine-tuning trajectory of the piston stroke, and the stress response curve from the hydraulic system. This data includes real-time changes in flow rate, piston movement trajectory, and stress under different operating conditions. Flow data is obtained from the flow signal output by the servo motor, representing the flow velocity and volume of the fluid in the hydraulic system. The piston stroke trajectory is recorded in each cycle by detecting the displacement and velocity of the piston using the servo system and sensors. The stress response curve is obtained by stress sensors in the hydraulic system collecting real-time pressure and stress information to reflect the operating conditions of the hydraulic components under different loads. This paper utilizes a tensor data structure to integrate time-series information on flow rate, path, and stress, constructing a dynamic tensor mapping field. The collected three-dimensional data is integrated into a tensor data structure. A tensor is a multi-dimensional array that can simultaneously carry multi-dimensional time-series information on flow rate, path, and stress. Time-series integration: Flow rate, path, and stress data are arranged according to the time dimension, forming a three-dimensional time-series data set. The flow rate, plunger stroke, and stress response at each time step correspond to an element of the tensor. Dynamic mapping: A tensor mapping field is constructed based on the changes in the three-dimensional data. This mapping field describes the relationship between flow rate, path, and stress, as well as their dynamic evolution over time. This model can capture the interaction between flow rate and plunger trajectory under different operating conditions and reflect how stress fluctuates with changes in flow rate and stroke. Local perturbation enhancement processing is applied to the tensor mapping field to identify flow abrupt changes and stress overload regions. After constructing the dynamic tensor mapping field, further local perturbation enhancement processing is performed to enhance the model's sensitivity to flow abrupt changes and stress overloads. By enhancing the impact of local perturbations on the tensor mapping field, the system can capture details of flow fluctuations and stress concentration areas. Specific methods may include high-frequency perturbation simulation or local precision amplification processing. Based on changes in the dynamic tensor mapping field, flow abrupt changes and stress overload regions are identified. These points typically correspond to areas where the system is unstable or has potential faults, such as sudden changes in flow or abnormal stress concentrations. Through this process, the system can detect abnormal operating states in advance, providing important basis for subsequent intervention decisions and fault diagnosis.

[0022] In the flow identification module, the process of determining whether there is a wave-wear coupling sensitive point is as follows: The system employs cross-screening of abnormal flow paths and stress concentration areas in the tensor model to extract a set of potential wear regions. First, the system filters out potential wear regions based on abnormal flow paths and stress concentration areas in the dynamic tensor model. These regions are typically the most significant areas of flow fluctuation and stress overload in the hydraulic system. The system identifies path segments with drastic flow changes by analyzing the time series of flow data in the tensor mapping field. These abnormal paths may be affected by load changes, flow fluctuations, or other disturbances. Stress response curves are used to identify areas of stress concentration, pressure overload, or severe deformation in the hydraulic system. These areas often overlap with abnormal flow paths, forming potential wear regions. The intersection of abnormal flow paths and stress concentration areas is extracted to form a set of potential wear region mappings. These regions are typically high-risk points for wear because they are simultaneously affected by flow fluctuations and high stress loads. The coupling relationship between flow rate change rate and path stability is analyzed. If the coupling factor shows periodic amplification in a specific path segment, it is marked as a wear-sensitive point. The system analyzes the coupling relationship between flow rate change rate and path stability to find potential wear-sensitive points. The flow rate change rate in each cycle is calculated to identify the frequency and amplitude of flow fluctuations, paying particular attention to situations that may lead to system instability, such as sudden or abrupt flow changes. The stability of the plunger path is analyzed, especially phenomena such as plunger trajectory drift, hysteresis, and oscillation. These unstable paths may lead to excessive friction and increased local wear in the system. By calculating the coupling factor between flow rate change rate and path stability, the periodic fluctuation of the coupling factor in a specific path segment is observed. If the coupling factor shows significant periodic amplification in a specific path segment, and the fluctuation amplitude gradually increases, it indicates that there is a risk of increased wear in that path segment, and the system marks this area as a wear-sensitive point. Further analysis of historical wear trends and current thermal drift status confirms whether the system falls within a fluctuation-wear coupling zone with potential linkage risks. If so, the frequency converter control mechanism is triggered. The analysis also confirms the existence of a linkage risk involving fluctuation-wear coupling and triggers appropriate control mechanisms. Historical wear trends: Analysis of historical system wear data helps understand the long-term development trend of wear and identifies worn components or areas. Historical data provides crucial reference for identifying wear-sensitive points. Current thermal drift status: Temperature sensors monitor the thermal drift of the servo system. Thermal drift can cause thermal expansion of hydraulic components and increased friction, accelerating the wear process. Abnormal current thermal drift status may further exacerbate wear. Linkage risk analysis: Combining historical wear trends and thermal drift status, the analysis determines whether a linkage risk involving fluctuation-wear coupling exists in a specific area. For example, in certain path segments, flow fluctuations and stress concentrations may interact with wear trends, forming a vicious cycle; triggering the frequency conversion control mechanism: if the system determines that there is a linkage risk of fluctuation-wear coupling in a certain sensitive area, and the preset wear risk threshold is reached, the frequency conversion control mechanism is triggered to adjust the system's operating parameters, slow down the wear process in that area, and extend the system's lifespan.

[0023] Dynamic control module: Based on the disturbance window and coupling sensitive point, activate the frequency conversion control strategy set of the servo drive layer, integrate thermal inertia parameters to make dynamic power constraint judgment, and determine whether there is structural thermal drift feedback imbalance. If so, enter the adaptive synchronization optimization module. The dynamic control module determines whether there is a structural thermal drift feedback imbalance process as follows: The system collects temperature distribution maps and servo response hysteresis parameters from multiple pump units to form a thermal feedback matrix for the current cycle. Temperature sensors installed at key locations within the pump units acquire the local temperature of each unit at different times. These sensors cover the main operating areas of the pump assembly, including hydraulic components, servo motors, and transmission devices. The system also records real-time feedback data from the servo system, particularly the hysteresis time between the control signal and the actual response. Hysteresis may be due to structural deformation, friction, or other thermal misalignment caused by thermal effects. Combining the collected temperature distribution maps with the servo response hysteresis parameters forms the thermal feedback matrix for the current cycle. This matrix demonstrates the relationship between different thermal zones and servo feedback, providing fundamental data for subsequent thermal drift analysis. By combining historical thermal response curves and temperature rise trend models, the development path of thermal drift is predicted and its impact on system regulation delay is analyzed. Through long-term collected historical thermal response data, the relationship between temperature changes and servo system response is analyzed. This data helps identify whether thermal drift gradually affects system performance and the changing trend of thermal feedback within each cycle. Based on historical temperature rise data, a temperature rise trend model can be established. These models predict possible development paths of thermal drift by fitting the temperature rise rate within the current cycle and long-term accumulated temperature data, including the rate and range of temperature rise and possible hysteresis effects. Based on the temperature rise trend model, the development path of thermal drift in the future period is predicted. At this point, the system not only focuses on the temperature rise trend but also needs to consider the potential negative impacts of thermal drift, especially its delay on system regulation response. The impact analysis of thermal drift on system delay involves comparing the predicted thermal drift path with the servo system response time to assess whether thermal drift exacerbates control delay. If temperature rise and thermal drift show significant delays in relation to the servo control system response, the system needs to take early warning measures. If the servo control response and thermal drift curve show an inverse correlation, and the offset time window continuously exceeds the set feedback tolerance, it is determined to be a thermal drift feedback imbalance state. By comparing the servo control response curve and the thermal drift curve, the relationship between them is examined. If, over multiple cycles, it is found that the servo control response time or response accuracy shows a negative correlation with the increase in temperature, it may indicate that thermal drift has affected the system's control performance. The system sets a "feedback tolerance time window," meaning that under normal circumstances, the servo control response should maintain a certain degree of synchronization with the thermal drift curve. If the inverse correlation trend continues and the offset exceeds the tolerance time window, it can be considered a feedback imbalance caused by thermal drift. This tolerance time window is used to eliminate short-term interference factors, ensuring that only long-term system offsets caused by thermal drift are judged as feedback imbalances. When the servo response and thermal drift curve continuously show an inverse correlation trend, and the offset time window continuously exceeds the set feedback tolerance, the system determines it to be a thermal drift feedback imbalance state, marks the abnormal state, and triggers relevant intervention logic, such as adjusting control parameters, starting the cooling system, or issuing alarm information.

[0024] Synchronization optimization module: Combining preset lifespan curves and abnormal response backtracking channels, it dynamically adjusts servo redundancy and buffer response strategies, and outputs a set of synchronization control commands.

[0025] The process of outputting the set of synchronization control instructions in the synchronization optimization module is as follows: The system comprehensively analyzes the servo redundancy configuration, buffer adjustment strategy, and thermal stability adaptation parameters output by the adaptive optimization module to generate a multi-axis coordinated drive scheme. The system obtains the servo redundancy configuration, buffer adjustment strategy, and thermal stability adaptation parameters from the adaptive optimization module. This information is typically obtained by monitoring the system's operating status in real time and combining it with predictive algorithms to calculate the optimal servo control configuration and thermal management strategy. Based on the redundancy requirements of the multi-axis control system, the optimal allocation method for different servo axes is calculated. The redundancy configuration can be dynamically adjusted based on load, thermal stability, and other real-time data to ensure the operating efficiency and stability of each servo unit. Considering potential load abrupt changes, transition states, or shocks in the system, the system uses a buffer adjustment strategy to avoid excessive system vibration or overload. This strategy is typically adjusted based on the dynamic characteristics of the system response. Based on current temperature monitoring and the thermal response model, the thermal stability of each servo unit is evaluated to determine which areas may be affected by overheating. Thermal adaptation parameters ensure that the system can maintain stable operation even at high temperatures, avoiding thermal imbalance or excessive temperature rise. The system generates a multi-axis coordinated drive scheme based on the status and requirements of each servo unit, based on the above analysis. This solution takes into account redundant configuration, load balancing, thermal stability and buffer adjustment to ensure that the system can operate stably under dynamic loads and complex working environments; Based on the coordinated drive scheme, the pressure increase / depression rhythm waveform is extracted, and the pulse servo command sequence is adjusted according to the plunger stroke compensation requirements. Extracting the pressure increase / depression rhythm waveform: Based on the generated coordinated drive scheme, the system generates pressure increase / depression rhythm waveforms according to different operating modes. This waveform is used to depict the pressure changes and other related adjustment requirements within each cycle, ensuring that the system's pressure fluctuations are controlled within a reasonable range. Adjusting the pulse servo command sequence according to the plunger stroke compensation requirements: The plunger stroke is one of the key motion parameters in the system, which may be affected by factors such as pressure, load, or temperature, resulting in instability or deviation. To compensate for these deviations, the system adjusts the corresponding pulse servo command sequence according to the plunger stroke compensation requirements. Each pulse command corresponds to a specific servo axis and stroke adjustment, ensuring that the plunger can run precisely according to the designed trajectory. Stroke compensation for each cycle is adjusted through pulse servo commands. The system generates precise pulse commands based on the dynamic state of each cycle; these commands typically include parameters such as acceleration, speed, and required torque. Based on real-time monitoring data, such as plunger position, speed, and pressure fluctuations, the system dynamically adjusts the compensation commands. Compensation requirements may vary depending on different operating conditions or environmental changes. Therefore, the system needs to be flexible and adaptive to form a final set of synchronous control commands, including command number, action period, target pressure regulation amount and thermal feedback coupling coefficient.

[0026] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0027] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A smart pressure boosting and depressurization control system for a homogenizer based on servo synchronous transmission, characterized in that, include: Linkage Identification Module: Through the high-frequency feedback data of the multi-axis servo actuator, the inertial difference of each plunger mechanism in the multi-pump parallel structure is extracted. Combined with the cycle phase drift and real-time load micro-change information, a synchronous offset vector map spectrum is generated, and it is determined whether the pressure increase and decrease intervention logic is triggered. If so, the cycle reconstruction module is entered. The beat reconstruction module: Based on the synchronous offset vector map spectrum, it calls the sliding registration algorithm and the inertial field decoupling network to perform deep fitting and repair of the beat micro-skew in the piston reciprocating path. At the same time, it integrates the thermal stability threshold curve to calculate the correction intensity factor and determine whether there is a linkage abnormal coupling. If so, it enters the flow disturbance identification module. Flow identification module: Extracts the reconstructed plunger stroke and pressure response mapping data, constructs a three-dimensional flow-path-stress tensor model, and uses a pulse flow mutation identification algorithm to calibrate the instantaneous disturbance window during the pressure increase and decrease process, and determines whether there are fluctuation-wear coupling sensitive points. If so, it enters the dynamic frequency conversion control module. Dynamic control module: Based on the disturbance window and coupling sensitive point, activate the frequency conversion control strategy set of the servo drive layer, integrate thermal inertia parameters to make dynamic power constraint judgment, and determine whether there is structural thermal drift feedback imbalance. If so, enter the adaptive synchronization optimization module. Synchronization optimization module: Combining preset lifespan curves and abnormal response backtracking channels, it dynamically adjusts servo redundancy and buffer response strategies, and outputs a set of synchronization control commands.

2. The intelligent boosting and depressurization control system for a homogenizer based on servo synchronous transmission according to claim 1, characterized in that, The logic process for determining whether to trigger stress reduction / decompression intervention is as follows: By periodically collecting the cycle synchronization, piston stroke difference, and pressure change rate from the multi-axis servo feedback, an inertial offset mapping matrix for the current working cycle is constructed. The matrix is ​​compared with the system's preset dynamic threshold model. If the beat offset exceeds the threshold range or the inertial response changes abruptly, it is determined to be a synchronization imbalance event. When a synchronous imbalance event is detected, the response phase difference between pump groups and the load distribution trend are further analyzed. If the response phase difference is in a continuous divergent state, the pressure increase / decrease intervention logic is triggered, and the cycle reconfiguration process is initiated.

3. The intelligent boosting and depressurization control system for a homogenizer based on servo synchronous transmission according to claim 2, characterized in that, The process of calling the sliding registration algorithm and decoupling the inertial field network is as follows: By deconstructing the real-time motion trajectory of the plunger system, a set of sliding path vectors for multiple time periods is constructed. An inertial coupling identification submodule is introduced to map the path vector set to the inertia tensor domain and separate the inertial coupling factors related to internal friction and hydraulic feedback of the structure. A sliding registration algorithm is used to perform similarity regression on the path offset of adjacent cycles, identify abnormal sliding points, and activate the inertial field decoupling network.

4. The intelligent boosting and depressurization control system for a homogenizer based on servo synchronous transmission according to claim 3, characterized in that, The deep fitting and repair process for the micro-skewness of the piston's reciprocating path is as follows: High-frequency variation samples of piston stroke under multiple cycles are extracted to construct a fitting benchmark set for cycle drift; By integrating the thermal deformation coefficient of the plunger structure with the hydraulic hysteresis model, the sample data are subjected to time-domain alignment and offset factor normalization. Based on the weighted minimum residual fitting method, the beat correction value for each cycle is dynamically calculated to generate a fitting compensation vector.

5. The intelligent boosting and depressurization control system for a homogenizer based on servo synchronous transmission according to claim 4, characterized in that, The determination of whether an abnormal coupling process has occurred is as follows: The repaired beat data is input into the linkage analysis model to calculate the response correlation matrix between each servo axis. Determine whether the correlation is trending towards an unbalanced state. If the decrease in multi-axis correlation exceeds the preset coupling threshold, it is determined that there is a phenomenon of linkage coupling attenuation. By combining the thermal stability threshold curve and the current load balancing status, a linkage anomaly scoring index is constructed. If the scoring index exceeds the coupling tolerance range, it is identified as linkage anomaly coupling.

6. The intelligent boosting and depressurization control system for a homogenizer based on servo synchronous transmission according to claim 5, characterized in that, The process of constructing a three-dimensional flow-path-stress tensor model is as follows: The system collects real-time output flow data from the servo unit, the piston stroke fine-tuning trajectory, and the stress response curve from the hydraulic system. By integrating time-series information from three dimensions—flow, path, and stress—using tensor data structures, a dynamic tensor mapping field is constructed. Local perturbation enhancement processing is applied to the tensor mapping field to identify flow abrupt change points and stress overload regions.

7. The intelligent boosting and depressurization control system for a homogenizer based on servo synchronous transmission according to claim 6, characterized in that, The process for determining whether there is a fluctuation-wear coupling sensitive point is as follows: Cross-filtering of abnormal flow paths and stress concentration areas in the tensor model to extract the mapping region set of potential wear areas; Analyze the coupling relationship between the flow rate change rate and path stability. If the coupling factor shows periodic amplification in a specific path segment, it is identified as a wear-sensitive point. By further combining historical wear trends with the current thermal drift status, it can be confirmed whether it belongs to a fluctuation-wear coupling area with linkage risk. If so, the frequency conversion control mechanism is triggered.

8. The intelligent boosting and depressurization control system for a homogenizer based on servo synchronous transmission according to claim 7, characterized in that, To determine whether a structural thermal drift feedback imbalance process exists: Collect the temperature distribution map of the multi-pump unit structure and the servo response hysteresis parameters to form the thermal feedback matrix for the current cycle; By combining historical thermal response curves and temperature rise trend models, the development path of thermal drift is predicted and its impact on system regulation delay is analyzed. If the servo control response and the thermal drift curve show an inverse correlation trend, and the offset time window continuously exceeds the set feedback tolerance, it is determined to be a thermal drift feedback imbalance.

9. The intelligent boosting and depressurization control system for a homogenizer based on servo synchronous transmission according to claim 8, characterized in that, The process of outputting the set of synchronization control instructions is as follows: By comprehensively analyzing the servo redundancy configuration, buffer adjustment strategy, and thermal stability adaptation parameters output by the adaptive optimization module, a multi-axis coordinated drive scheme is generated. Based on the coordinated drive scheme, the waveform diagram of the pressure increase and decrease rhythm is extracted, and the pulse servo command sequence is adjusted according to the piston stroke compensation requirements to form the final set of synchronous control commands.

Images