Ebnite rubber roller production method based on intelligent temperature and pressure regulation and control

Abstract

The invention discloses an Ebnite rubber roller production method based on temperature and pressure intelligent regulation and control, and relates to the technical field of rubber roller production, and the method comprises the following steps: constructing a temperature collection credibility function according to a local temperature abnormal distribution matrix, carrying out fitting comparison on the temperature response of each collection point and a target temperature rise curve, and obtaining a target temperature rise curve; and generating a credibility index for judging the credibility of the temperature data, and correcting the judgment logic of temperature acquisition according to the abnormal change of the local temperature under the condition of abnormal heat conduction caused by air resistance in the vulcanization heating process. The problem of temperature control misjudgment caused by abnormal local heat conduction due to formation of air resistance in the vulcanizing and heating process of the Ebnite rubber roller is solved, dynamic identification and self-adaptive regulation and control on abnormal temperature and pressure are realized, sufficient vulcanization, uniform structure and stable performance of each area of the rubber roller are ensured, and the product quality and the service reliability are improved.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of rubber roller production, in particular to an Ebnite rubber roller production method based on intelligent temperature and pressure control. BACKGROUND

[0002] The Ebnite rubber roller production based on intelligent temperature and pressure control is a new manufacturing method that combines sensor monitoring, intelligent control algorithm and rubber vulcanization process optimization. The core goal is to realize dynamic, accurate and closed-loop adjustment of the two key parameters of temperature and pressure in the production process of the Ebnite rubber roller, so as to improve the mechanical properties, structural density and dimensional stability of the rubber roller. The existing Ebnite rubber roller production technology based on intelligent temperature and pressure control mainly arranges temperature and pressure sensors in the vulcanization equipment to collect the temperature and pressure data inside and on the surface of the rubber roller body in real time, and transmits the collected data to the industrial control system. Through the embedded PID regulator, fuzzy control algorithm or pre-set vulcanization model, the data is analyzed and judged, and then the heating system (such as an electric heating plate or a steam heating system) and the pressurizing system (such as a hydraulic mechanism or a pneumatic device) are dynamically adjusted based on the pre-set process curve to ensure uniform temperature distribution and moderate pressure stability during the vulcanization process. This allows rubber molecules to fully crosslink and bubbles to be effectively discharged, avoiding defects such as under-vulcanization or over-vulcanization, internal cavities and uneven hardness that are common in traditional processes. The entire process usually includes a preheating and prepressing stage, a temperature and pressure rising stage, a constant temperature and pressure vulcanization stage, a temperature and pressure decreasing stage, and a final demolding and cooling stage. Each stage is adjusted under the coordination of the intelligent control system, thereby realizing high consistency, low energy consumption and automatic production of high-performance Ebnite rubber roller products.

[0003] The existing technology has the following disadvantages: During the production of the Ebnite rubber roller based on intelligent temperature and pressure control, the rubber roller may form a local air block between the contact surface of the rubber and the mold due to the small deformation of the mold cavity or insufficient rubber exhaust during the vulcanization temperature rising stage, which may cause the heat conduction efficiency in this area to decrease and the local temperature to rise slowly. Since this "thermal lag area" is not caused by insufficient heating power, but by abnormal heat conduction path, the existing Ebnite rubber roller production technology based on intelligent temperature and pressure control cannot correct the temperature collection judgment logic according to the abnormal local temperature change caused by the air block during the vulcanization temperature rising process, thereby mistakenly judging the overall temperature state as having met the standard and entering the constant temperature control stage prematurely. The above control error will cause the vulcanization reaction in the local area to be incomplete, resulting in insufficient crosslinking of the rubber roller and forming structural weaknesses that are prone to fatigue damage, uneven strength or interlayer peeling during service, which seriously affects the product quality and service life.

[0004] The above information disclosed in the BACKGROUND section merely to enhance the understanding of the background of the present disclosure, and therefore it can include information that does not constitute prior art known to those of ordinary skill in the art. SUMMARY

[0005] The purpose of the present application is to provide an Ebnite rubber roller production method based on temperature and pressure intelligent regulation to solve the problems in the background.

[0006] To achieve the above-mentioned purpose, the present application provides the following technical scheme: an Ebnite rubber roller production method based on temperature and pressure intelligent regulation, specifically comprising the following steps: S1, collecting time series temperature data and pressure response data at different spatial positions between the Ebnite rubber roller and the mold, and constructing a thermal behavior feature field containing temperature gradient change characteristics and pressure phase characteristics, for determining whether there is a gas resistance leading to abnormal heat conduction in the vulcanization temperature rising process; S2, in the presence of gas resistance leading to abnormal heat conduction, a difference mapping model is established based on the thermal behavior feature field, the temperature waveform delay, heat diffusion curvature and temperature rise slope offset are calculated, and a local temperature abnormal distribution matrix is generated, for determining the local temperature abnormal change in the presence of gas resistance leading to abnormal heat conduction in the vulcanization temperature rising process; S3, constructing a temperature collection credibility function according to the local temperature abnormal distribution matrix, fitting and comparing the temperature response of each collection point with the target temperature rising curve, generating a credibility index for judging the credibility of temperature data, and correcting the judgment logic of temperature collection according to the local temperature abnormal change in the presence of gas resistance leading to abnormal heat conduction in the vulcanization temperature rising process; S4, reconstructing the judgment logic of temperature collection according to the temperature collection credibility index, using a multi-parameter joint determination structure to classify and identify the temperature rising state, and adjusting the temperature determination node, the temperature rising duration and the heat input distribution scheme; S5, calculating the temperature and pressure balance coefficient based on the judgment logic correction result, synchronously comparing the temperature output and pressure response in the temperature rising stage, and executing real-time temperature and pressure adjustment strategy to realize dynamic regulation of the temperature rising process.

[0007] Preferably, S1 specifically comprises: Temperature collection units and pressure collection units are arranged in the contact area of the Ebnite rubber roller and the mold along the radial and axial directions, the temperature data and pressure response data of each spatial position are synchronously obtained by setting a time series sampling period, and the correspondence between the sampling points and the spatial coordinates is established in time sequence, for forming a time series temperature data and pressure response data set at different spatial positions; The time series temperature data and the pressure response data are matched and calculated according to the spatial coordinates, the temperature gradient change rate and the pressure phase difference between adjacent collection units are calculated, a multi-dimensional parameter matrix containing the temperature gradient change characteristics and the pressure phase characteristics is constructed, and the multi-dimensional parameter matrix is spatially mapped to form a thermal behavior characteristic field, which is used to reflect the thermal and pressure coupling relationship between the Ebnite rubber roller and the mold; The temperature gradient change characteristic parameters and the pressure phase characteristic parameters in the thermal behavior characteristic field are jointly compared and analyzed, and when the temperature gradient change characteristics appear discontinuous mutation and the pressure phase characteristics synchronously deviate, it is determined that there is a gas resistance leading to abnormal heat conduction in the vulcanization temperature rising process.

[0008] Preferably, S2 specifically includes the following steps: S201, in the presence of a gas resistance leading to abnormal heat conduction, a difference mapping model is constructed based on the thermal behavior characteristic field, the temperature gradient change characteristics and the pressure phase characteristics of the normal region and the abnormal region in the thermal behavior characteristic field under the same spatial path are compared point by point, the spatial response difference parameters are extracted, and the parameters are mapped to a unified thermal behavior reference grid to reflect the heat conduction path change characteristics under the interference of gas resistance; S202, on the basis of the difference mapping model, the temperature change curve of each spatial node in the thermal behavior characteristic field is analyzed by using the time series offset analysis method, the temperature waveform delay is calculated to identify the heat conduction time lag, the heat diffusion curvature is calculated by three-point fitting to identify the heat flow turning or focusing area, and the temperature rise slope offset is obtained by difference calculation to quantify the local heating abnormal trend; S203, the temperature waveform delay, the heat diffusion curvature and the temperature rise slope offset are constructed into a local temperature abnormal distribution matrix in the order of spatial nodes, and the local temperature abnormal change region in the presence of a gas resistance leading to abnormal heat conduction in the vulcanization temperature rising process is identified by matching the multi-index coupling results in the matrix with the threshold value, and the spatial coordinates and the thermal characteristic label corresponding to the region are output.

[0009] Preferably, S202 specifically includes: On the basis of the difference mapping model, the temperature change curve of each spatial node in the thermal behavior characteristic field is time normalized, the temperature change sequences of different nodes are aligned by time index by setting a unified sampling time interval, a temperature sequence set with a synchronous time reference is formed, and is used for subsequent time series offset analysis; In the temperature sequence set, a pair of temperature change curves of adjacent spatial nodes is selected, the time offset between the curves is calculated by a sliding window to obtain the temperature waveform delay parameter, and the numerical change rate of adjacent temperature points is fitted by a three-point method to calculate the heat diffusion curvature, and then the local curvature distribution of the heat flow direction is obtained; The time-continuous sampling values of each node in the temperature sequence set are subjected to a difference operation to obtain a temperature rise rate change quantity and coupled with a heat diffusion curvature data to extract a temperature rise slope offset quantity to represent a local heating trend change feature and output in a parameter group form for a subsequent matrix generation process.

[0010] Preferably, S3 specifically comprises the following steps: S301, according to the temperature waveform delay, heat diffusion curvature and temperature rise slope offset quantity of each spatial node in the local temperature anomaly distribution matrix, a three-dimensional heat anomaly feature vector set is constructed, a credible weight corresponding to each feature dimension is set, a node-level heat behavior disturbance value is generated by weighted vector calculation, and is used to construct a temperature collection credibility function; S302, the heat behavior disturbance value output by the temperature collection credibility function is compared with the temperature response data of each collection point, the temperature response data is curve-fitted with a target temperature rise curve based on a sliding window method, a fitting residual and a response delay difference index are calculated, and are used to quantify the heat response offset degree of the collection point; S303, the heat response offset degree and the temperature collection credibility function result are weighted and fused to generate a credibility index for judging the credibility of the temperature data, the judgment logic of the temperature collection is corrected according to the credibility index, the collection point credibility level, the determination trigger condition and the time tolerance range are adjusted, and the responsive identification of the local temperature abnormal change and the collection strategy optimization are realized.

[0011] Preferably, S302 specifically comprises: The heat behavior disturbance value output by the temperature collection credibility function is compared with the temperature response data of each collection point according to the spatial coordinate order, the one-to-one correspondence of the heat behavior disturbance value and the temperature response data of each collection point is realized by establishing a time synchronization index table, a matching data set is formed, and synchronous data input is provided for curve fitting analysis; In the matching data set, the temperature response data segment in the continuous time window is selected, the sliding window method is applied to slide in sequence with a set window width and step, the least square fitting algorithm is used to curve-fit the temperature response data with the target temperature rise curve, the fitting residual value and the response delay difference value at each window position are recorded, and the local temperature rise response offset is captured; The fitting residual and the response delay difference index of all sliding windows are normalized to generate a heat response offset curve reflecting the heat response offset of each collection point in the entire temperature rise process, and through the fluctuation frequency and amplitude analysis of the offset curve, a stable deviation interval is extracted and a heat response offset degree parameter set is formed to provide an input data basis for subsequent credibility index calculation.

[0012] Preferably, S4 specifically comprises: According to the temperature collection credibility index, the credibility levels of all temperature collection points are divided, low credibility points are removed, and a credibility index table is generated, a one-to-one mapping relationship between the index table and the thermal behavior disturbance distribution is established, the judgment logic of temperature collection is reconstructed, and the reconstructed logic is used as the input prerequisite structure of the judgment system; On the basis of the reconstructed judgment logic, the temperature collection credibility index, the thermal response offset degree and the spatial node characteristics are integrated to construct a joint judgment structure containing multiple parameter dimensions, the density clustering and support vector classification algorithm are used to classify the temperature state, and the classification labels of the stable state, thermal lag state and nonlinear fluctuation state are outputted; According to the temperature state classification label, the judgment strategy parameters of temperature collection are updated, the selection strategy and distribution density of temperature judgment nodes are dynamically adjusted, the target interval of temperature duration is reset, and the power proportion of each heat input path is optimized, so that the heat input distribution scheme is reconstructed in time sequence and spatial dimensions to adapt to the change characteristics of the real temperature state in the vulcanization process.

[0013] Preferably, S5 specifically is: According to the temperature collection credibility index and the thermal response offset degree of each spatial node in the judgment logic correction result, the temperature change gradient and the pressure response gradient in the time sequence are jointly extracted, a temperature-pressure characteristic parameter set is constructed, a temperature-pressure balance coefficient is calculated by using a weighted fusion method, and the coupling relationship change degree of temperature output and pressure response in the temperature rising stage is quantified; In the temperature rising stage, the temperature output and the pressure response are compared synchronously according to the temperature-pressure balance coefficient, the dynamic change trajectories of temperature and pressure at each time are compared by establishing a synchronous time index table, the delay alignment point and the synchronous offset trend of the temperature-pressure response curve are identified by using a sliding window algorithm, and a temperature-pressure alignment offset curve for judging the thermal pressure coordination in the temperature rising process is generated; Based on the synchronous offset values of each time period in the temperature-pressure alignment offset curve, an adaptive adjustment algorithm is used to construct a real-time temperature-pressure adjustment strategy, the heat input power distribution and the pressure loading rate in the temperature rising stage are dynamically adjusted according to the sampling period, the control parameters are corrected in time when the temperature-pressure coupling offset exceeds the control tolerance range, and the temperature-pressure synchronous control and dynamic stable matching in the temperature rising process are realized.

[0014] In the above technical scheme, the technical effects and advantages provided by the present application are: 1、The present application can accurately judge the abnormal problem of heat conduction path caused by gas blockage during the vulcanization temperature rising process by constructing a thermal behavior characteristic field and identifying the coupling anomaly between temperature gradient change characteristics and pressure phase characteristics. On this basis, the system uses difference mapping modeling and multi-parameter thermal response characteristic analysis method to effectively identify the local temperature rising lag area, and quantitatively evaluates the temperature collection data through the reliability function, realizes the identification and distinction of the thermal abnormal disturbance area, and then corrects the problem of premature termination of the temperature rising process caused by false judgment of the standard temperature in the traditional temperature control system. The response logic constructed based on the change law of physical field improves the decision reliability and control accuracy of the temperature collection data, and effectively avoids the structure defects caused by local vulcanization deficiency.

[0015] 2、The present application realizes the closed-loop optimization control system from data collection judgment, state recognition to control strategy execution by introducing intelligent judgment mechanism such as reliability index, multi-parameter joint determination structure and temperature-pressure balance coefficient. The sliding window curve fitting and thermal response offset identification method is used in the temperature rising process, which not only improves the accuracy of temperature rising state classification, but also provides basis for the dynamic matching of subsequent heat input power and pressure loading rate. Finally, through the adaptive adjustment algorithm, the closed-loop response of thermal pressure coupling regulation is realized, so that the temperature and pressure regulation process is more fine and real-time, and the stability, adaptability and product quality consistency of the vulcanization process under complex working conditions are significantly improved. The overall technical scheme strengthens the identification and control ability of non-ideal heat transfer state, and is suitable for the molding process of rubber products with various complex cavity structures, and has significant engineering popularization and application value. BRIEF DESCRIPTION OF DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed in the embodiments will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments described in the present application, and other drawings can also be obtained by those skilled in the art based on these drawings.

[0017] Figure 1 The flowchart of the Ebnite rubber roller production method based on temperature and pressure intelligent regulation of the present application. DETAILED DESCRIPTION

[0018] Example implementations will now be described more fully with reference to the accompanying drawings. Example implementations may, however, be implemented in many different forms and should not be construed as limited to the examples set forth herein; rather, these example implementations are provided so that this disclosure will be thorough and complete, and will fully convey the inventive aspects to those skilled in the art.

[0019] The present application provides a method for producing an Ebnite rubber roller based on temperature and pressure intelligent regulation, comprising the following steps: Figure 1The Ebnite rubber roller production method based on temperature and pressure intelligent regulation shown specifically comprises the following steps: S1, collecting time series temperature data and pressure response data of different spatial positions between the Ebnite rubber roller and the mold, and constructing a thermal behavior characteristic field containing temperature gradient change characteristics and pressure phase characteristics, for determining whether there is abnormal heat conduction caused by air block during the vulcanization temperature rising process; In this embodiment, S1 specifically comprises: Arranging temperature acquisition units and pressure acquisition units in the contact area of the Ebnite rubber roller and the mold along the radial and axial directions, synchronously acquiring temperature data and pressure response data of each spatial position by setting a time series sampling period, and establishing a corresponding relationship between the sampling points and the spatial coordinates in time sequence, for forming time series temperature data and pressure response data sets of different spatial positions; In the process of arranging temperature acquisition units and pressure acquisition units in the contact area of the Ebnite rubber roller and the mold along the radial and axial directions, micro thermocouples and piezoelectric sensors can be embedded in multiple specific positions on the inner wall of the mold and the periphery of the rubber roller. Each thermocouple is used to continuously collect the real-time temperature change of the point where it is located, and the piezoelectric sensor is used to record the pressure response of the point. The sampling system triggers all sensors at the same time at a set time series period, and stores the sampling data in time sequence. Spatial positioning is achieved by labeling the absolute position coordinates of each collection point in the rubber roller coordinate system during installation, and embedding position information tags in the data stream. In this way, temperature and pressure data streams at different spatial positions covering the entire contact area can be formed, and synchronous acquisition in time and space dimensions can be achieved. In this way, the real distribution state of heat and pressure transmission between the rubber and the mold can be obtained, which facilitates the subsequent construction of a characteristic field with analytical ability, and further provides a basis for accurately judging heat conduction abnormalities.

[0020] The temperature acquisition unit takes a miniature thermocouple or an optical fiber temperature sensor as a core component, has high time resolution and high temperature response sensitivity, can operate stably for a long time in a high-temperature environment of rubber vulcanization, and accurately reflects the small temperature rise change of a local area. The pressure acquisition unit usually adopts a thin film piezoresistive sensor or a piezoelectric ceramic sensor, has strong repeatability and small nonlinear error, and can accurately sense the instantaneous pressure fluctuation in the mold closing process. These sensors are embedded between the rubber contact surface and the mold edge through a customized packaging material and bonding process, ensuring that the normal molding process is not disturbed, and the collected signal is not distorted due to high temperature or elastic interference. Each acquisition unit is physically mapped by coding, and the time alignment and spatial positioning of different unit data are performed by a synchronous acquisition controller at the signal processing end, so as to realize the one-to-one correspondence of temperature data and pressure response data at the same spatial position and the same time point, and form a high-resolution thermal pressure state distribution map. Through this acquisition configuration, a refined original data set can be established to provide accurate basis for subsequent analysis of thermal behavior abnormalities.

[0021] The time series temperature data and pressure response data are matched and calculated according to the spatial coordinates, the temperature gradient change rate and the pressure phase difference between adjacent acquisition units are calculated, a multi-dimensional parameter matrix containing temperature gradient change characteristics and pressure phase characteristics is constructed, and the multi-dimensional parameter matrix is spatially mapped to form a thermal behavior characteristic field for reflecting the thermal and pressure coupling relationship between the Ebnite rubber roller and the mold; The time series temperature data and pressure response data are matched and calculated according to the spatial coordinates, which can be realized by synchronous matching through the spatial point coordinate index established before acquisition. Each data acquisition unit is assigned a unique three-dimensional coordinate identifier during acquisition, and the system merges the time series of temperature and pressure data according to the same coordinate point when processing data. In the calculation process, a pair of data paths is first established between adjacent spatial acquisition units, the temperature values of each pair of acquisition points at the same time are differentiated, and the actual physical distance between the two points is divided to obtain the temperature gradient change rate; similarly, the phase offset of the corresponding pressure response curve is calculated and mapped as a standardized index. Taking two points in the axial direction of a rubber roller as an example, if the temperature changes rapidly at the front position and the temperature changes lag at the rear position, and the corresponding pressure response is obviously advanced or delayed, a bidirectional feature point with high temperature gradient change rate and large pressure phase difference can be constructed. The temperature gradient change rate and the pressure phase difference of all adjacent sampling pairs are filled into a three-dimensional parameter matrix according to the spatial topological relationship, and the spatial reconstruction is performed according to the point coordinates, and finally a thermal behavior characteristic field for showing the thermal and pressure change linkage characteristics is formed. This processing method can reveal the micro dynamic behavior caused by uneven thermal and pressure or gas resistance during the vulcanization process of the rubber roller.

[0022] The time series temperature data refers to a sequence of continuously recorded temperature change values, which can reveal the thermal dynamic curve trend of a sampling point in the heating process; the pressure response data refers to the corresponding pressure change trajectory at the same position, which is used to reflect the real-time evolution of the mold closing and the rubber pressure state. Spatial coordinate matching means that the temperature data and the pressure data have a unified reference point in the three-dimensional coordinate system, so that accurate pairing analysis can be realized. The temperature gradient change rate is an index for measuring the strength of heat propagation in space, and its abnormal increase usually indicates that heat diffusion is blocked. The pressure phase difference is used to describe the time sequence difference between the pressure signals of adjacent regions, and is an important parameter for identifying air block interference or local delayed response. The multi-dimensional parameter matrix is formed by structurally arranging the temperature gradient change rate and the pressure phase difference between each point, which has directionality and spatial continuity. The thermal behavior characteristic field is the result of mapping the above parameter matrix to the actual spatial topology, which can be regarded as a holographic expression of the thermal and pressure coupling state between the Ebnite rubber roller and the mold, and provides a quantifiable data basis for subsequent identification of abnormal regions and judgment of air block influence.

[0023] The temperature gradient change characteristic parameter and the pressure phase characteristic parameter in the thermal behavior characteristic field are jointly compared and analyzed. When a discontinuous mutation of the temperature gradient change characteristic and a synchronous shift of the pressure phase characteristic are detected, it is determined that there is an air block causing abnormal heat conduction in the vulcanization heating process.

[0024] The process of joint comparison and analysis of the temperature gradient change characteristic parameter and the pressure phase characteristic parameter in the thermal behavior characteristic field can be realized through the parameter mapping relationship of each spatial node in the thermal behavior characteristic field. First, arrange the temperature gradient change characteristic parameters in spatial sequence, calculate the gradient change trend between consecutive nodes, and detect whether the change rate appears discontinuous characteristics such as sudden jump or direction reversal; then, compare the time sequence curve of the pressure phase characteristic parameter with the temperature gradient change trend synchronously, and identify the relative shift amplitude of the two in the same spatial interval. When the temperature gradient change trend is suddenly interrupted in a certain region, and at the same time the pressure phase curve is delayed or advanced relative to the adjacent region, it indicates that the heat conduction process is locally blocked, i.e. the heat transfer path is disturbed, and it can be judged that there is an air block phenomenon in the region. Taking the actual production scene as an example, when the mold local contact surface retains air during the rubber roller vulcanization process, the temperature gradient curve of the region presents a nonlinear sudden drop, and the pressure phase curve appears abnormal delay, and the two characteristics coincide in spatial position, i.e. the formation of heat conduction abnormality. Through this joint comparison and analysis logic, the heat conduction obstacle caused by air block can be accurately identified without relying on manual judgment, providing a reliable trigger basis for subsequent logic correction.

[0025] The temperature gradient change characteristic parameter is used to describe the change of the diffusion rate of heat between different spatial nodes, and the continuity thereof reflects whether the heat flow conduction path is unobstructed. When the parameter appears discontinuous mutation, it means that the heat conduction of a certain region is blocked or delayed. The pressure phase characteristic parameter is used to depict the response synchronization of the pressure signal in the time dimension, and the change thereof is directly related to the dynamic behavior of the rubber after being heated and expanded and compressed. When the pressure phase characteristic occurs synchronous offset, it means that the mechanical response of the local region is out of synchronization with the thermal behavior, which is usually caused by gas barrier or conduction delay. The joint comparison analysis is a calculation method of fusing the temperature gradient characteristic and the pressure phase characteristic in the spatial and time dimensions. By cross-checking the mutual coupling trend of the two groups of parameters, the abnormal coordination phenomenon of heat conduction and pressure transmission can be revealed. The abnormal situation of heat conduction caused by air resistance is the region where the existence of heat field mutation and pressure offset is synchronized in this comparison. The identification result of the region is directly fed back to the judgment logic correction module, which is used for dynamic adjustment of the subsequent temperature control strategy.

[0026] S2, in the presence of abnormal heat conduction caused by air resistance, a difference mapping model is established based on the thermal behavior characteristic field, the temperature waveform delay, the heat diffusion curvature and the temperature rise slope offset are calculated, and a local temperature abnormal distribution matrix is generated, which is used to determine the local temperature abnormal change in the presence of abnormal heat conduction caused by air resistance in the vulcanization temperature rising process; In this embodiment, S2 specifically comprises the following steps: S201, in the presence of abnormal heat conduction caused by air resistance, a difference mapping model is established based on the thermal behavior characteristic field, the temperature waveform delay, the heat diffusion curvature and the temperature rise slope offset are calculated, and a local temperature abnormal distribution matrix is generated, which is used to determine the local temperature abnormal change in the presence of abnormal heat conduction caused by air resistance in the vulcanization temperature rising process; Under the premise of abnormal heat conduction caused by gas blockage, the temperature and pressure response of some areas in the thermal behavior characteristic field deviate from the normal warming behavior. The construction of the difference mapping model can be achieved by selecting representative normal areas and suspected abnormal areas in the thermal behavior characteristic field, and comparing the temperature gradient change characteristics and pressure phase characteristics of the same spatial path point by point. In specific implementation, the temperature change rate and pressure response phase difference of each node in the spatial path can be extracted by using equal-step sampling method to form a set of two-dimensional comparison sequences. By calculating the difference values of the characteristic parameters of the two areas in the same spatial path, such as temperature gradient mutation point and pressure fluctuation lag point, a set of spatial response difference parameters is obtained. Then, these parameters are mapped to the uniformly constructed thermal behavior reference grid to form a difference mapping map through two-dimensional interpolation or three-dimensional thermal field reconstruction, so as to show the abnormal heat conduction path caused by gas blockage, such as local counterflow area or heat accumulation area deviating from the main heat flow direction. This mapping structure can directly reveal the spatial area of thermal coupling imbalance and provide data support for subsequent judgment of local abnormal points.

[0027] The thermal behavior characteristic field is a high-dimensional space-time field constructed by integrating the temperature gradient change and pressure phase response of each spatial point between the Ebnite rubber roller and the mold, reflecting the dynamic coupling behavior of heat and pressure. The temperature gradient change characteristic refers to the change rate of temperature value along the spatial path, which is used to capture the spatial distribution law of heat conduction efficiency. The pressure phase characteristic refers to the relative time offset of pressure response at different points at the time of heat input, which indirectly reflects the delay or lag of the internal pressure change of the rubber. The spatial response difference parameter is a difference index based on the above two characteristics, which is used to quantify the deviation degree of normal area and suspected abnormal area in heat conduction behavior. The unified thermal behavior reference grid is a spatial reconstruction structure, which provides structural uniformity for multi-area thermal behavior comparison through normalized coordinates and parameter distribution, and ensures the comparability of difference values in the same reference system. The difference mapping model not only constructs the "deviation map", but also provides a structured and visualized analysis method for complex thermal abnormal behavior, which is the key basis for identifying non-uniform thermal barrier influence.

[0028] S202, on the basis of the difference mapping model, a time series offset analysis method is used to analyze the temperature change curve of each spatial node in the thermal behavior characteristic field, to calculate the temperature waveform delay to identify the heat conduction time lag, to calculate the heat diffusion curvature based on the three-point method fitting to identify the heat flow turning or focusing area, and to obtain the temperature rise slope offset by difference calculation to quantify the local heating abnormal trend; S203, construct the local temperature abnormal distribution matrix by arranging the temperature waveform delay, heat diffusion curvature and temperature rise slope offset in the order of the space nodes, and identify the local temperature abnormal change area in the heat conduction abnormal situation caused by air resistance in the vulcanization temperature rising process by matching the multi-index coupling results in the matrix with the threshold value, and output the corresponding space coordinates and thermal characteristic label of the area.

[0029] The process of constructing the local temperature abnormal distribution matrix is to arrange the three key thermal behavior characteristic parameters of temperature waveform delay, heat diffusion curvature and temperature rise slope offset in the order of the arrangement of the space nodes, and fill them into a three-dimensional data matrix point by point. Each space node occupies a row in the matrix, and the corresponding three columns record the waveform delay, diffusion curvature and temperature rise slope offset of the node in the heat conduction process, thereby forming a unified structure data set. In order to realize the identification of the local temperature abnormal change area, a set of threshold intervals generated based on historical production data statistics can be designed to screen the characteristic values in each column. For example, set the upper limit of the waveform delay, the negative value interval of the diffusion curvature, and the threshold of the steep growth of the slope offset, and realize the multi-index coupling abnormal identification of the node by judging whether the three parameters of the node meet the abnormal conditions at the same time. If a node is marked as abnormal, its space coordinates and three index values will be extracted and output as a thermal characteristic label set for subsequent control strategy adjustment and temperature and pressure compensation model calling. By integrating multi-dimensional thermal behavior indicators into a single matrix and performing coupling determination, the discrimination accuracy of complex thermal barrier phenomena can be significantly improved.

[0030] The temperature waveform delay in this process is a parameter for evaluating the time lag of heat transfer, which is usually obtained by identifying the offset of the starting point of the thermal response through a sliding window. The heat diffusion curvature describes the turning or gathering characteristics of the heat flow in the spatial distribution, which can reflect the disturbance effect of the structure on the heat flow. The temperature rise slope offset quantifies the abnormal trend of the temperature change rate, revealing whether the heating intensity appears nonlinear growth in the local area. These three characteristics jointly represent the abnormality of the heat conduction path from the dimensions of time, space and dynamic change. The constructed local temperature abnormal distribution matrix not only retains the spatial topological relationship of each node, but also integrates its thermal behavior state, ensuring that the identification result has consistency and traceability in the physical space. The output of the space coordinates facilitates the positioning of the key intervention area in the temperature rising strategy, while the generation of the thermal characteristic label provides quantitative basis for intelligent decision-making. Through this means, the heat lag distribution caused by air resistance can be systematically captured, thereby realizing early warning and intelligent intervention of local abnormalities in the vulcanization process.

[0031] In this embodiment, S202 specifically comprises: On the basis of the difference mapping model, the temperature change curve of each space node in the thermal behavior characteristic field is time normalized, and by setting a uniform sampling time interval, the temperature change sequences of different nodes are aligned by time index to form a temperature sequence set with a synchronous time reference, which is used for subsequent time sequence offset analysis; After the difference mapping model is constructed, the temperature change curve of each space node in the thermal behavior characteristic field needs to be time normalized to ensure that the data at different positions have a uniform time reference basis. In specific implementation, a fixed sampling time interval can be first set, and the temperature data of all space nodes can be resampled to this interval, and the data is aligned by linear interpolation, spline interpolation or Fourier interpolation, so as to construct a temperature change sequence with consistent time. The time index in each sequence is strictly unified, ensuring that the temperature data of each node at any time point can be directly compared horizontally. Through this processing, a temperature sequence set with a synchronous time reference can be formed, so that the response sequence between nodes can be clearly identified when subsequent time sequence offset analysis is performed. For example, when the temperature rise of a node lags behind that of other nodes by one complete sampling period, it can be considered as a preliminary sign of thermal conduction resistance at this position. In this process, the "time normalization processing" is used to eliminate non-structural time sequence errors caused by acquisition delay, communication interference or local thermal capacity difference; the "uniform sampling time interval" ensures the comparability of all temperature sequences; and the "alignment by time index" provides a time sequence basis for subsequent temperature waveform delay, thermal diffusion curvature and temperature rise slope calculation, so that the whole thermal behavior analysis has strict time consistency and calculability.

[0032] In the temperature sequence set, the temperature change curves of adjacent space nodes are selected, the time offset between the curves is calculated by a sliding window to obtain the temperature waveform delay parameter, and the numerical change rate of adjacent temperature points is fitted by a three-point method to calculate the thermal diffusion curvature, and then the local curvature distribution of the heat flow direction is obtained; The temperature change curve pairs of adjacent spatial nodes in the temperature sequence set can be paired based on the spatial coordinate relationship of the nodes in the thermal behavior characteristic field, and then the sliding window analysis method is applied to compare the time response difference between each pair of curves. In specific implementation, one reference curve is kept stationary, and the other target curve is translated point by point in the time dimension. By calculating the mean square error of the two curves at each position in the window, the position with the minimum error is found as the time offset point, and the temperature waveform delay parameter of the curve pair is obtained. This parameter reflects the actual conduction time difference of heat between the two adjacent nodes. Subsequently, the three-point method is used to fit the adjacent temperature values of each node to calculate the temperature change rate at the node, and the second derivative of the fitting results of the three adjacent nodes is calculated to obtain the thermal diffusion curvature, which reveals the curvature change of the heat flow when it propagates in space, thereby determining whether there is focusing, reflection or deviation of heat. For example, when the thermal diffusion curvature is negative and shows a continuous downward trend, it can be determined that the heat flow has a turning-back or blocking behavior. In this way, the sliding window provides a response difference analysis method in the time dimension, and the three-point method captures the shape change of the heat flow in the spatial dimension. The combination of the two can systematically identify the dynamic behavior of heat propagation in complex structures, which helps to reveal the local thermal lag or energy accumulation area caused by air resistance, and has significant significance for the quantitative identification of abnormal heat conduction.

[0033] The time-continuous sampling values of each node in the temperature sequence set are subjected to difference operation to obtain the temperature rise rate change amount, which is coupled with the thermal diffusion curvature data to extract the temperature rise slope offset amount to represent the local heating trend change feature, and output in the form of parameter groups for subsequent matrix generation process calling.

[0034] The time-continuous sampling values of each node in the temperature sequence set are subjected to difference operation, so as to quantify the temperature change rate in a unit time, that is, to obtain the temperature rise rate change. When implemented, the temperature value at each time point can be subtracted from the temperature value at the previous time point point by point, and then divided by the sampling time interval, to form a rate sequence with the same length as the original temperature sequence. The rate sequence can reveal the response strength and change rhythm of different nodes in the temperature rise process. Subsequently, the temperature rise rate change is coupled with the thermal diffusion curvature obtained in the previous calculation step point by point. The coupling processing can adopt normalization fusion or weight superposition, etc. The temperature change rate and the heat flow curvature are taken as double-factor indexes to jointly construct the temperature rise slope offset, which reflects whether the abnormal thermal diffusion curvature of a node is accompanied by a mutation of the temperature rise rate. For example, when the thermal diffusion curvature of a node is extremely large and the temperature rise rate increases sharply, it usually indicates that the local heat energy focusing leads to abnormal temperature rise trend, and is easy to form a local overheating area. By organizing the temperature rise slope offset of each node in the form of a vector and naming it as a parameter group, it is convenient to directly quote in subsequent construction of the local temperature abnormal distribution matrix, and to serve as an important basis for identifying the thermal lag area. The method comprehensively considers the time dynamic change and the space thermal field curvature degree, and has higher thermal anomaly positioning accuracy.

[0035] S3, constructing a temperature collection credibility function according to the local temperature abnormal distribution matrix, fitting and comparing the temperature responses of each collection point with a target temperature rise curve, generating a credibility index for judging the credibility of the temperature data, and using the credibility index to correct the judgment logic of the temperature collection according to the local temperature abnormal change caused by the abnormal heat conduction due to the gas resistance existing in the vulcanization temperature rise process; In the embodiment, S3 specifically includes the following steps: S301, constructing a three-dimensional thermal anomaly feature vector set according to the temperature waveform delay, the thermal diffusion curvature and the temperature rise slope offset of each spatial node in the local temperature abnormal distribution matrix, setting the credibility weight corresponding to each feature dimension, generating a node-level thermal behavior disturbance value through vector weighted calculation, and using the thermal behavior disturbance value to construct a temperature collection credibility function; In order to extract the core data from the local temperature anomaly distribution matrix that helps to judge the credibility of the thermal anomaly, first of all, the temperature waveform delay, thermal diffusion curvature and temperature rise slope offset of each spatial node in the matrix need to be standardized, and the numerical dimension of different physical quantities needs to be unified. Then, a three-dimensional thermal anomaly feature vector is constructed for each node, which corresponds to the behavior characteristics of temperature response in time, space diffusion and heating rate. In order to highlight the credibility of different features in judgment, the credibility weight of each dimension should be set according to the experience data or machine learning model result, for example, the weight of the thermal diffusion anomaly can be increased in the case of more sensitivity. Next, the three-dimensional features and corresponding weights are calculated by weighted vector, and the thermal behavior disturbance value of each node is obtained by the inner product summation. The disturbance value quantifies the misleading degree of the node's thermal behavior to the vulcanization state judgment, which can be used as the basic input to construct the temperature collection credibility function. Through this structured processing, not only the three types of key abnormal information are retained, but also the sensitivity and stability of subsequent fitting judgment are improved.

[0036] The temperature waveform delay reflects the time lag of the temperature response of a certain collection point in the heating process relative to the ideal curve, revealing the existence of resistance in the heat conduction path of the point. The thermal diffusion curvature measures the degree of deflection of the temperature field in the process of spatial propagation, and if the curvature of a certain point is abnormal, it may mean that there is a heat flow convergence or dispersion phenomenon in this area. The temperature rise slope offset represents the deviation between the heating rate of a certain point and the expected rate during the heating process, which is a key parameter for revealing the imbalance of local heating efficiency. The three-dimensional thermal anomaly feature vector is a structural unit constructed with these three types of physical parameters as dimensions, which is used to identify the thermal anomaly degree of each node in the spatial dimension. The feature credibility weight is a set of preset weighting coefficients, which is set according to the decision-making influence of each physical dimension in the actual control, and is used to emphasize the contribution of different features to the overall credibility judgment. The node-level thermal behavior disturbance value is the weighted calculation result based on the feature vector and the weight vector, which is a quantitative evaluation of the temperature judgment ability of the collection point, and is used for weight adjustment or confidence weighting when constructing the temperature collection credibility function.

[0037] S302, the thermal behavior disturbance value output by the temperature collection credibility function is compared with the temperature response data of each collection point, and the temperature response data is fitted with the target temperature curve based on the sliding window method, and the fitting residual and response delay difference index are calculated to quantify the thermal response deviation of the collection point; S303, the thermal response deviation and the temperature collection credibility function result are weighted and fused to generate a credibility index for judging the credibility of the temperature data, and the judgment logic of the temperature collection is modified according to the credibility index, the collection point is adjusted, the judgment trigger condition and the time tolerance range are adjusted, and the response identification and collection strategy optimization of the local temperature abnormal change are realized.

[0038] To realize the responsive identification of local temperature abnormal change and the optimization of collection strategy, firstly, the heat response offset degree and the temperature collection credibility function result need to be weighted and fused. The specific implementation includes: constructing a weighted fusion model, setting the weight proportion of the heat response offset degree and the heat behavior disturbance value in different feature dimensions, and using linear weighting or Bayesian probability weighting method to combine the two to generate a credibility index. The credibility index is a comprehensive evaluation of the reliability of the temperature data of the collection point. The higher the value, the lower the credibility of the temperature data. In actual implementation, multiple credibility threshold levels can be set, and the temperature collection judgment logic is dynamically modified according to the credibility index. For example, when the credibility index of a collection point exceeds the set threshold, the collection level of the point in the subsequent temperature control process is lowered, the weight of the point in the temperature control decision is reduced, and the severity of the trigger condition is increased to extend the time tolerance range of the point to avoid misjudgment risk. If multiple adjacent collection points have high credibility index at the same time, a local abnormal temperature rise warning can be issued, and a local heating compensation model can be called to perform a response action. Through this process, the heat conduction abnormal area can be effectively identified and the collection strategy can be corrected, and the temperature data decision logic in the heating process can be dynamically adapted.

[0039] The heat response offset degree reflects the time sequence stability and deviation of the temperature response, and is a stability index evolved from the sliding window residual curve; the temperature collection credibility function is a multi-dimensional weight function constructed from spatial heat behavior abnormal features, and outputs a numerical result reflecting the heat behavior disturbance intensity. The weighted fusion of the two can take into account the time continuity feature and the spatial abnormal feature, and improve the accuracy of temperature data credibility judgment. The credibility index is a single discriminant index generated after fusion, which is convenient for directly calling control logic to set the judgment threshold and behavior response. The collection level adjustment is a dynamic control mechanism for the weight of a single point data, and the setting of the trigger condition and the time tolerance range determines whether the data point participates in the control decision of the current stage. This structure has significant adaptability and error tolerance, and is an optimization and upgrade of the traditional static temperature collection strategy.

[0040] In this embodiment, S302 specifically includes: The heat behavior disturbance value output by the temperature collection credibility function is paired and compared with the temperature response data corresponding to each collection point in the order of spatial coordinates, and a time synchronization index table is established to realize one-to-one correspondence between the heat behavior disturbance value and the temperature response data of each collection point, forming a matched data set to provide synchronous data input for curve fitting analysis; In order to realize the effective comparison of the thermal behavior disturbance value and the temperature response data, firstly, the thermal behavior disturbance value and the temperature response data are respectively mapped according to each collection point based on the spatial coordinates. On this basis, by setting a unified time sampling frequency and a synchronous time stamp, a time synchronization index table is constructed to ensure the correspondence of different data sources in the time dimension. The index table pairs the thermal behavior disturbance value of each collection point at each time node with the corresponding temperature response data to form a matching data set with a two-way correspondence. For example, if the disturbance value of a certain position suddenly changes at the initial stage of temperature rise, and the temperature response curve does not appear synchronous fluctuation, the response lag characteristic can be identified in the subsequent curve fitting. This way makes the subsequent fitting analysis no longer dependent on a single data source, but analyzes the temperature curve trend under the consideration of thermal disturbance, thereby improving the sensitivity and robustness of the fitting result to thermal anomalies. In the technical features, the thermal behavior disturbance value represents the thermal anomaly risk weight of the collection point, the temperature response data is the measured value of the temperature rise behavior corresponding to the point, the time synchronization index table ensures the time sequence consistency between the data, the spatial coordinate sequence is used to maintain the consistent pairing logic of the point, and the matching data set is the core input structure for subsequent mathematical modeling and judgment correction.

[0041] In the matching data set, the temperature response data segment in the continuous time window is selected, the sliding window method is applied to set the window width and step to slide in sequence, the least square fitting algorithm is used to perform curve fitting on the temperature response data and the target temperature rise curve, and the fitting residual value and the response delay difference value at each window position are recorded to capture the local temperature rise response deviation in time; In order to accurately capture the offset characteristics of the local warming behavior in the time dimension, the temperature response data segment within the continuous time window can be selected in the matching data set, and the sliding window method is used for analysis. The sliding window method is a local sequence analysis method, by setting a fixed window width and step, the analysis window is gradually sliding on the temperature response data according to the time axis, ensuring that each fitting focuses on the response characteristics in the local time period. For the data segment in each window, the least square fitting algorithm is applied to fit the temperature response data of the sampling points to the target warming curve. The target warming curve is an ideal temperature rising track constructed according to the normal warming rule, which has a fixed heating slope and time response model. The least square fitting algorithm can evaluate the deviation between the temperature response data and the target warming curve in the local time window by solving the function that minimizes the sum of squares of errors. Through this process, two key parameters can be extracted: one is the fitting residual value, which is used to represent the numerical deviation between the real response and the ideal warming in each window, and the other is the response delay difference value, which is obtained by comparing the time axis offset of the fitting curve and the target curve to identify the lag behavior of the temperature response. In the technical features, the sliding window method is used to realize the local time sequence analysis, the least square fitting algorithm realizes the accurate curve comparison modeling, the target warming curve is used as the standard reference to ensure the consistency of judgment, and the three are combined to form a high-resolution warming offset identification method.

[0042] The fitting residual and response delay difference indicators of all sliding windows are normalized to generate a thermal response offset curve reflecting the thermal response offset of each collection point in the entire warming process. By analyzing the fluctuation frequency and amplitude of the offset curve, the stable deviation interval is extracted and the thermal response offset degree parameter set is formed, which provides the input data basis for the subsequent credibility index calculation.

[0043] In order to extract the thermal response anomaly characteristics of each acquisition point from the overall time dimension, it is necessary to normalize the fitting residual and response delay difference indicators obtained in all sliding windows. The purpose of normalization is to unify the values of different scales and units to the same interval, so that they have comparability and fusion. The range normalization or Z-score standardization method is often used to standardize the mapping of each indicator. After normalization, the residual and delay difference of the same acquisition point in multiple time windows can be combined into a continuous data stream to build a complete thermal response offset curve. This curve reflects the evolution trend of the response offset of the acquisition point in the entire heating stage. The fluctuation frequency represents the periodicity of the temperature response anomaly, and the fluctuation amplitude represents the strength of the abnormal response. By extracting the frequency characteristics through Fourier transform or sliding standard deviation analysis method, and combining with the local extreme point identification method to extract the fluctuation amplitude, the time section with stable temperature response offset can be accurately determined. Record these stable deviation intervals in the form of parameter set, and combine time, amplitude and frequency dimensions to build the thermal response offset degree parameter set, which provides structured input for subsequent calculation of temperature data reliability index. In this process, normalization calculation ensures the collaborative analysis of each dimension data, thermal response offset curve provides the basis for time series analysis, and deviation interval extraction realizes the accurate definition of abnormal behavior.

[0044] S4, according to the temperature acquisition reliability index, the judgment logic of temperature acquisition is reconstructed, the heating state is classified and recognized by using a multi-parameter joint judgment structure, and the temperature judgment node, the heating duration and the heat input distribution scheme are adjusted; In this embodiment, S4 is specifically: According to the temperature acquisition reliability index, the reliability level of all temperature acquisition points is divided, the low reliability points are removed, and a reliability index table is generated. Through the index table, a one-to-one mapping relationship with the thermal behavior disturbance distribution is established, the judgment logic of temperature acquisition is reconstructed, and the reconstructed logic is used as the input prerequisite structure of the judgment system; To realize the effective utilization of temperature collection credibility index, firstly, all temperature collection points are classified by preset credibility classification rules, and the classification is based on the comprehensive score of multiple parameters including the fitting residual of temperature waveform and target curve, the thermal response offset degree, and the local thermal anomaly characteristic weight factor. Each collection point is classified into high credibility, medium credibility, or low credibility level after scoring. For low credibility points, their data may be affected by factors such as air resistance interference, sensor drift, or thermal inertia lag, so directly participating in temperature control judgment will lead to system misjudgment, therefore these points are excluded in the subsequent logic. Then, the remaining high and medium credibility points are numbered and a credibility index table is generated, which represents the dual information of each node in the spatial coordinates and data credibility dimension. Then, the index table is mapped with the previously formed thermal behavior disturbance distribution data point by point, constructing the corresponding structure between the thermal anomaly area distribution and the credibility distribution, providing reliable data basis and regional identification accuracy for the reconstruction of the subsequent judgment logic.

[0045] The "temperature collection credibility index" represents the credibility level of each collection point's temperature data in the statistical and dynamic response dimensions during the vulcanization temperature rise process; "credibility level classification" refers to the classification of collection points based on comprehensive characteristic values; "exclusion of low credibility points" reflects the strategy of excluding abnormal or disturbed points; "credibility index table" is a structured data set that establishes a relationship between the spatial position and credibility level of the remaining collection points; "thermal behavior disturbance distribution" refers to the spatial disturbance area image calculated based on multi-dimensional thermal anomaly indicators in the thermal behavior characteristic field; "one-to-one mapping relationship" refers to the accurate pairing of credible collection points with positions in the thermal disturbance map; "reconstruction of temperature collection judgment logic" means that after excluding interference and strengthening the effective data basis, the input boundary and analysis process of the temperature rise determination model are re-established; "input premise structure of the determination system" means that this reconstructed logic will serve as the input condition framework for the core decision model of subsequent state recognition, control instruction judgment, etc. Through this technical path, the data input quality of the control system can be guaranteed from the source, and the accuracy and robustness of temperature and pressure control judgment can be improved.

[0046] Based on the reconstructed judgment logic, the temperature collection credibility index, thermal response offset degree, and spatial node characteristics are integrated to build a joint determination structure containing multiple parameter dimensions, and the density clustering and support vector classification algorithms are used to classify the temperature rise state, outputting the classification labels of stable state, thermal lag state, and nonlinear fluctuation state; To improve the accuracy of temperature state determination in the heating stage, the thermal response offset degree and spatial node characteristics are further integrated on the basis of the temperature collection credibility index to construct a joint determination structure containing multiple parameter dimensions. This structure takes each temperature collection point as the basic unit to construct a feature vector group, with vector dimensions including thermal response stability index, temperature rise rate offset, thermal diffusion curvature, spatial distribution coordinates, and temperature fluctuation periodicity information. On this basis, the density clustering algorithm is introduced to identify the distribution characteristics of temperature states in high-dimensional parameter space. Density clustering does not depend on the number of preset categories and is suitable for identifying nonlinear and irregular state boundaries, so it can effectively aggregate points in similar thermal behavior patterns. Then, the support vector classification algorithm is used to train the label learning of these clustering results to construct a discriminant function for online classification, outputting spatial classification labels of stable state, thermal lag state, and nonlinear fluctuation state to provide a refined identification basis for thermal control strategy execution.

[0047] The "reconstructed judgment logic" refers to the new judgment system for temperature state analysis formed after the pre-sequence collection point credibility is removed and the logic structure is reorganized. The "temperature collection credibility index" reflects the quantitative characteristics of each data point in the sampling credibility dimension; the "thermal response offset degree" represents the response difference degree caused by abnormal heat transfer path or local medium structure; the "spatial node characteristics" refer to the spatial position, thermal history, and relative layout between adjacent nodes of each collection point inside the mold; the "joint determination structure" is a model framework that integrates multiple dimension input features for unified classification judgment; the "density clustering algorithm" is an unsupervised learning method based on local density function construction, which can automatically identify the natural clustering trend of sample points and adapt to irregular boundaries, typical algorithms such as DBSCAN; the "support vector classification algorithm" is a supervised learning method based on the idea of maximum interval hyperplane to realize multi-class segmentation, suitable for high-dimensional small sample classification tasks; the "heating state classification label" is one of the algorithm output results, corresponding to the three typical behavior states in the temperature control process, facilitating accurate state formulation of control response in the subsequent execution stage. Through this combination strategy, structured intelligent classification of the heating process can be realized from the perspective of thermal response mechanism, greatly enhancing the identification sensitivity and response reliability of nonlinear heat transfer abnormalities.

[0048] According to the heating state classification label, the parameters of the temperature collection determination strategy are updated, the selection strategy and distribution density of the temperature determination node are dynamically adjusted, the target interval of the heating duration is re-set, and the power proportion of each heat input path is optimized to realize the linkage reconstruction of the heat input distribution scheme in the time sequence and spatial dimensions to adapt to the changing characteristics of the real heating state in the vulcanization process.

[0049] The judgment strategy parameters of temperature collection are updated according to the temperature state classification label, and dynamic adjustment can be realized by constructing a feedback type thermal control adaptive mechanism. First, for the space region marked as thermal hysteresis state, the distribution density and selection sensitivity of the temperature judgment node are increased, so that the abnormal region is more densely covered, and the temperature fluctuation details can be captured in real time; for the stable state region, the node density is appropriately reduced to reduce data redundancy. On this basis, the target interval of the temperature rise duration is reset, and the upper and lower limits of the temperature rise process control time are dynamically adjusted by analyzing the change trend and time delay coefficient of the thermal response curve. Next, the power ratio of the heat input path is adjusted in real time according to the temperature state classification result, for example, the heat input power of the region in the thermal hysteresis state is increased, and the rhythm heating mode is enabled for the region in the nonlinear fluctuation state to suppress the fluctuation, thereby optimizing the thermal energy distribution structure in the spatial dimension. Finally, the distribution logic of the temperature judgment node, the temperature rise time control strategy and the heat input path control are fused to form a linkage reconstruction model, so that the thermal control scheme has the ability to reconstruct in real time with the change of state, and fully matches the dynamic temperature rise behavior characteristics in the vulcanization process.

[0050] The "temperature state classification label" is one of the output results of the thermal behavior analysis model, indicating the physical state category of the current region temperature response, which usually includes stable state, thermal hysteresis state and nonlinear fluctuation state. The "temperature collection judgment strategy parameters" cover multiple key threshold settings and time control conditions for judging whether the temperature meets the standard or not, which is the basic rule system of the thermal control logic; the "selection strategy and distribution density of the temperature judgment node" refers to which points in the mold space are selected as the temperature judgment basis points and the arrangement density between these points, and the judgment granularity can be controlled by adjusting this parameter; the "target interval of the temperature rise duration" is the time length boundary of the thermal process control period, and by dynamically setting it, the temperature rise stage can be more in line with the actual rhythm of the thermal response; the "power ratio of the heat input path" describes the energy allocation ratio of different regional heating modules or heating channels, and optimizing the allocation can realize thermal field balance; the "linkage reconstruction of the heat input distribution scheme in time and space dimensions" means not only adjusting the heating intensity at different positions, but also starting, stopping or switching the heat source in time according to the real-time state, realizing the overall coordination and feedback optimization in time and space dimensions. This process strengthens the pertinence and responsiveness of heat input, effectively avoiding the problems of local insufficient vulcanization or heat accumulation caused by static strategy.

[0051] S5, based on the judgment logic correction result, calculate the temperature and pressure balance coefficient, compare the temperature output and pressure response in the temperature rise stage, and execute real-time temperature and pressure adjustment strategy to realize dynamic regulation of the temperature rise process.

[0052] In this embodiment, S5 is specifically: According to the temperature collection credibility index and the thermal response offset degree of each space node in the judgment logic correction result, the temperature change gradient and the pressure response gradient in the time series are extracted, a temperature-pressure characteristic parameter set is constructed, a temperature-pressure balance coefficient is calculated by using a weighted fusion method, and the temperature-pressure balance coefficient is used for quantifying the coupling relationship change degree of the temperature output and the pressure response in the heating stage; In the heating stage of the Ebnite rubber roller, the cooperative change relationship between the temperature output and the pressure response directly affects the effective heat transfer and the stability of the molding process. In order to accurately evaluate this relationship, the temperature collection credibility index and the thermal response offset degree of each space node can be obtained according to the judgment logic correction result, and the temperature change gradient and the pressure response gradient of each node in the same time period are extracted by combining the real-time collected time series temperature data and pressure data. The temperature change gradient can be calculated by the temperature difference and the time difference of adjacent sampling points, and the pressure response gradient is determined by monitoring the pressure loading change rate. After normalization processing of these parameters, a comprehensive temperature-pressure balance coefficient is generated by fusion according to the set weighting coefficient. The coefficient can quantify the coordination between the current heat input and the pressure response, and a high balance value represents good heat-pressure synchronization, and a low balance value indicates that there is a mismatch between heat conduction and pressure loading. For example, if the pressure rises rapidly and the temperature response lags in the early heating stage, the balance coefficient will decrease, prompting the control system to adjust to avoid local undercuring.

[0053] The temperature collection credibility index is a quantitative indicator reflecting the reliability of the temperature data of each collection point, which is derived from the fitting residual and the response delay calculation result between the temperature response curve and the target heating curve; the thermal response offset degree is used to measure the deviation degree of the actual temperature response relative to the expected state, and both of them reflect the credibility and offset risk of the collected data. The temperature change gradient represents the change rate of temperature per unit time, which is an important basis for evaluating the heating speed and heat diffusion trend; the pressure response gradient is a quantitative of the time dynamic characteristics of pressure change, which reflects the change state of external pressure application. After classifying these parameters into a temperature-pressure characteristic parameter set, different weights are set for each parameter dimension to form the fused temperature-pressure balance coefficient. The coefficient not only reflects the change of single data, but also embodies the interactive coupling characteristics between multiple parameters, providing accurate input basis for heat-pressure matching control in the heating process.

[0054] In the heating stage, the temperature output and the pressure response are compared synchronously according to the temperature-pressure balance coefficient, the dynamic change trajectories of temperature and pressure at each time are compared by establishing a synchronous time index table, the delay alignment point and the synchronous offset trend of the temperature-pressure response curve are identified by using a sliding window algorithm, and a temperature-pressure alignment offset curve for judging the heat-pressure coordination of the heating process is generated; In the heating stage of the Ebnite rubber roll vulcanization process, to achieve effective coupling control of temperature output and pressure response, the dynamic variation trajectories of both need to be compared in real time. This process can be achieved by constructing a synchronous time index table to pair temperature collection time points with corresponding pressure response time points, forming a complete time synchronization data structure. On this basis, the sliding window algorithm is applied to segmentally analyze the temperature and pressure response curves, and the time delay difference between the two is compared in sequence within the window to identify the temperature-pressure delay alignment points and synchronization offset trends in each time period. For example, if the pressure response curve lags behind the temperature curve significantly in a certain period at the beginning of vulcanization, the window detection can mark this time period as a temperature-pressure mismatch interval. The synchronization offset trends extracted in these periods are normalized and connected to form a continuous temperature-pressure alignment offset curve on the time axis, which dynamically reflects the real-time coupling coordination degree between heat and pressure. The smaller the fluctuation of this curve, the more synchronized the temperature and pressure response; the greater the fluctuation, the more uncoordinated the abnormal behavior between heat and pressure, which needs to trigger subsequent control strategies.

[0055] The temperature-pressure balance coefficient is a composite index calculated based on the dynamic characteristics of thermal behavior and pressure change, which is used to measure the stability of heat-pressure matching state; the synchronous time index table is a data structure established by one-to-one correspondence between temperature output and pressure response under the same time reference, making the data between different collection channels comparable in time sequence. Temperature output and pressure response are represented as two continuous time series signals, and the sliding window algorithm divides the two curves into small segments according to time dimension by setting fixed width and sliding step, and analyzes the time difference and form matching of each segment, which can accurately capture the instantaneous coupling misalignment point. The delay alignment point represents the best synchronization overlap position of temperature and pressure on the time axis, which is used to judge whether the response time difference is within the tolerable range; the synchronization offset trend records the trend of synchronization change on the time axis in each window segment, which is used as the basis for subsequent adjustment. The final output of the temperature-pressure alignment offset curve reflects the evolution trajectory of the dynamic coordination of heat and pressure in the whole heating process, which is an important basis for process control closed-loop regulation.

[0056] Based on the synchronization offset values of each time period in the temperature-pressure alignment offset curve, an adaptive adjustment algorithm is used to construct a real-time temperature-pressure adjustment strategy, which dynamically adjusts the heat input power distribution and pressure loading rate in the heating stage according to the sampling period, and adjusts the control parameters in time when the temperature-pressure coupling offset exceeds the control tolerance range, to achieve temperature-pressure synchronization control and dynamic stable matching in the heating process.

[0057] To realize the coordinated control of heat input and pressure loading in the heating stage, a real-time temperature and pressure adjustment strategy with responsiveness and self-regulation ability is constructed according to the synchronous offset values of each time period in the temperature and pressure alignment offset curve. This strategy can be realized through an adaptive adjustment algorithm. First, the temperature and pressure alignment offset value of the current period is read in each sampling period, and compared with the preset tolerance threshold. If the offset value is within the tolerance range, the current heat input power distribution and pressure loading rate are maintained. If the offset value exceeds the threshold, the spatial distribution proportion of the heat input power is adjusted in real time according to the offset direction and offset amplitude, for example, reducing the power density in the overheated area and increasing the pressure loading rate in the pressure lag area, so as to promote the response trajectory of temperature and pressure to tend to be synchronous again. For example, if it is observed that the temperature rises rapidly and the pressure response lags in a certain period, the system can automatically reduce the output power of the heating unit in this period, and at the same time, fine-tune the loading rhythm of the pressure head, so that the time sequence consistency of the two is restored. This mechanism dynamically corrects the control parameters in each sampling period through closed-loop regulation, ensures that the temperature and pressure responses maintain a dynamically stable matching state, and prevents local overheating or pressure imbalance.

[0058] The temperature and pressure alignment offset curve is a time series curve constructed by comparing the temperature and pressure responses in the time dimension through the sliding window algorithm, which reflects the synchronization of heat and pressure coupling. The synchronous offset value is the response offset between temperature and pressure calculated in each time period, including time delay and response difference. The adaptive adjustment algorithm is a control model based on the dynamic changes of offset trend and regulation target, which can automatically calculate the adjustment proportion coefficient according to the actual deviation amplitude, and realize the real-time correction of control parameters. The heat input power distribution refers to the proportion of electric heating or heat flow input allocated among different heating units or spatial regions, and the pressure loading rate represents the change rate of pressure applied per unit time. The regulation tolerance range is the preset fluctuation interval of temperature and pressure synchronization, and exceeding this range is considered as a mismatch state that needs to trigger the correction mechanism. Through continuous feedback and adjustment in the sampling period, the coupling balance of heat supply and pressure change in the heating process is realized, thereby improving the stability and precision of the vulcanization molding process.

[0059] The above-described embodiments can be implemented in part or in whole through software, hardware, firmware or any combination thereof. When implemented in software, the above-described embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When loaded and executed by a computer, the computer instructions or computer programs cause the computer to perform all or part of the processes or functions according to the embodiments of the present application. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable apparatus. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, from a website site, a computer, a server or a data center to another website site, a computer, a server or a data center through a wired or wireless (for example, infrared, wireless, microwave, etc.) manner. The computer-readable storage medium can be any available medium or a set of medium including one or more available medium that is accessible by a computer. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state disk.

[0060] It should be understood that the size of the sequence number of each process described above in various embodiments of the present application does not mean the order of execution, and the execution order of each process should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0061] Those skilled in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be realized in electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0062] In several embodiments provided in the present application, it should be understood that the disclosed system and method can be implemented in other ways. For example, the above-described embodiments are only illustrative, for example, the division of units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed each other can be indirect coupling or communication connection through some interface, device or unit, and can be electrical, mechanical or other forms.

[0063] The units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0064] In addition, each functional unit in each embodiment of the present application can be integrated into a processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit.

[0065] The above is only a specific embodiment of the present application, but the protection scope of the present application is not limited thereto, and any person skilled in the art can easily think of changes or replacements within the technical scope disclosed by the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for producing Ebnite rubber rollers based on intelligent temperature and pressure control, characterized in that, Specifically, the following steps are included: S1. Collect time-series temperature data and pressure response data at different spatial positions between the Ebnite rubber roller and the mold, and construct a thermal behavior feature field containing temperature gradient change characteristics and pressure phase characteristics to determine whether there is gas resistance causing abnormal heat conduction during the vulcanization heating process. S2. In the case of abnormal heat conduction caused by air resistance, a difference mapping model is established based on the thermal behavior characteristic field to calculate the temperature waveform delay, thermal diffusion curvature and temperature rise slope offset, and generate a local temperature anomalous distribution matrix to determine the local temperature anomalous changes in the case of abnormal heat conduction caused by air resistance during the sulfurization heating process. S3. Construct a temperature acquisition reliability function based on the local temperature anomalous distribution matrix, fit and compare the temperature response of each acquisition point with the target heating curve, generate a reliability index for judging the reliability of temperature data, and use it to correct the judgment logic of temperature acquisition based on the local temperature anomalous changes caused by gas resistance during the sulfurization heating process. S4. Reconstruct the judgment logic of temperature acquisition based on the reliability index of temperature acquisition, adopt a multi-parameter joint judgment structure to classify and identify the heating state, and adjust the temperature judgment node, heating duration and heat input distribution scheme. S5. Calculate the temperature and pressure balance coefficient based on the judgment logic correction result, and compare the temperature output and pressure response synchronously during the heating stage to execute a real-time temperature and pressure adjustment strategy to achieve dynamic control of the heating process.

2. The method for producing Ebnite rubber rollers based on intelligent temperature and pressure control according to claim 1, characterized in that, S1 specifically refers to: Temperature and pressure acquisition units are arranged radially and axially in the contact area between the Ebnite rubber roller and the mold. Temperature and pressure response data at each spatial location are acquired synchronously by setting a time series sampling period. The correspondence between sampling points and spatial coordinates is established in time order to form a time series temperature and pressure response dataset for different spatial locations. The time-series temperature data and pressure response data are matched and calculated according to spatial coordinates. By calculating the rate of change of temperature gradient and pressure phase difference between adjacent acquisition units, a multi-dimensional parameter matrix containing temperature gradient change characteristics and pressure phase characteristics is constructed. This multi-dimensional parameter matrix is ​​then spatially mapped to form a thermal behavior characteristic field, which is used to reflect the thermal and pressure coupling relationship between the Ebnite rubber roller and the mold. By jointly comparing and analyzing the temperature gradient change characteristic parameters and pressure phase characteristic parameters in the thermal behavior characteristic field, when a discontinuous abrupt change in the temperature gradient change characteristic and a synchronous shift in the pressure phase characteristic are detected, it is determined that there is an abnormal situation of heat conduction caused by gas resistance during the sulfurization heating process.

3. The method for producing Ebnite rubber rollers based on intelligent temperature and pressure control according to claim 1, characterized in that, S2 specifically includes the following steps: S201. In the case of abnormal heat conduction caused by air resistance, a difference mapping model is constructed based on the thermal behavior feature field. By comparing the temperature gradient change characteristics and pressure phase characteristics of the normal and abnormal regions in the thermal behavior feature field under the same spatial path, the spatial response difference parameter is extracted and mapped to a unified thermal behavior reference grid to reflect the heat conduction path change characteristics under air resistance interference. S202. Based on the difference mapping model, the time series offset analysis method is used to analyze the temperature change curve of each spatial node in the thermal behavior feature field, calculate the temperature waveform delay to identify the heat conduction time lag, calculate the heat diffusion curvature based on the three-point method to identify the heat flow return or focusing area, and obtain the temperature rise slope offset through differential calculation to quantify the local heating abnormal trend. S203. The temperature waveform delay, thermal diffusion curvature and temperature rise slope offset are constructed into a local temperature anomalous distribution matrix according to the spatial node order. By matching the results of multi-index coupling in the matrix with the threshold, the local temperature anomalous change region under the condition of abnormal heat conduction caused by gas resistance during the sulfurization heating process is identified, and the spatial coordinates and thermal feature labels of the corresponding region are output.

4. The method for producing Ebnite rubber rollers based on intelligent temperature and pressure control according to claim 3, characterized in that, S202 specifically refers to: Based on the difference mapping model, the temperature change curve of each spatial node in the thermal behavior feature field is time normalized. By setting a uniform sampling time interval, the temperature change sequences of different nodes are aligned with time index to form a temperature sequence set with a synchronous time reference for subsequent time series offset analysis. In the temperature sequence set, temperature change curve pairs of adjacent spatial nodes are selected. The time offset between each curve is calculated by sliding window to obtain the temperature waveform delay parameter. The numerical change rate of adjacent temperature points is fitted by the three-point method to calculate the thermal diffusion curvature, thereby obtaining the local curvature distribution of the heat flow direction. Differential operation is performed on the time-continuous sampled values ​​of each node in the temperature sequence set to obtain the change in temperature rise rate and couple it with the thermal diffusion curvature data to extract the temperature rise slope offset to characterize the local heating trend change features, and output it in the form of a parameter group for subsequent matrix generation process.

5. The method for producing Ebnite rubber rollers based on intelligent temperature and pressure control according to claim 1, characterized in that, S3 specifically includes the following steps: S301. Based on the temperature waveform delay, thermal diffusion curvature and temperature rise slope offset of each spatial node in the local temperature anomaly distribution matrix, construct a three-dimensional thermal anomaly feature vector set, set the confidence weights corresponding to each feature dimension, and generate node-level thermal behavior perturbation values ​​through vector weighting calculation, which are used to construct the temperature acquisition confidence function. S302. Compare the thermal behavior perturbation value output by the temperature acquisition confidence function with the temperature response data of each acquisition point, and perform curve fitting between the temperature response data and the target heating curve based on the sliding window method. Calculate the fitting residual and response delay difference index to quantify the degree of thermal response offset of the acquisition point. S303. The thermal response offset degree and the temperature acquisition credibility function result are weighted and fused to generate a credibility index for judging the credibility of temperature data. The judgment logic of temperature acquisition is corrected according to the credibility index, and the acceptance level of acquisition points, judgment trigger conditions and time fault tolerance range are adjusted to realize the responsive identification of local abnormal temperature changes and the optimization of acquisition strategy.

6. The method for producing Ebnite rubber rollers based on intelligent temperature and pressure control according to claim 5, characterized in that, S302 specifically refers to: The thermal behavior perturbation values ​​output by the temperature acquisition confidence function are paired and compared with the temperature response data corresponding to each acquisition point in spatial coordinate order. By establishing a time synchronization index table, a one-to-one correspondence between the thermal behavior perturbation values ​​and the temperature response data of each acquisition point is realized, forming a matching dataset, which provides synchronous data input for curve fitting analysis. In the matching dataset, select temperature response data segments within a continuous time window, apply the sliding window method to slide sequentially with a set window width and step size, and use the least squares fitting algorithm to fit the temperature response data with the target heating curve. Record the fitting residual value and response delay difference value at each window position to capture the local heating response shift in time. The fitting residuals and response delay differences of all sliding windows are normalized and calculated to generate thermal response offset curves that reflect the entire heating process of each sampling point. By analyzing the fluctuation frequency and amplitude of the offset curves, stable deviation intervals are extracted and a set of thermal response offset parameters is formed, providing input data basis for subsequent confidence index calculation.

7. The method for producing Ebnite rubber rollers based on intelligent temperature and pressure control according to claim 1, characterized in that, S4 specifically refers to: Based on the reliability index of temperature acquisition, all temperature acquisition points are classified into reliability levels, low reliability points are eliminated and a reliability index table is generated. A one-to-one mapping relationship between the index table and the distribution of thermal behavior disturbance is established, the judgment logic of temperature acquisition is reconstructed, and the reconstructed logic is used as the input premise structure of the judgment system. Based on the reconstructed judgment logic, the reliability index of temperature acquisition, the degree of thermal response offset and spatial node features are integrated to construct a joint judgment structure with multiple parameter dimensions. Density clustering and support vector classification algorithms are used to classify the heating state and output classification labels for steady state, thermal hysteresis state and nonlinear fluctuation state. The temperature acquisition judgment strategy parameters are updated based on the temperature rise status classification label. By dynamically adjusting the selection strategy and distribution density of temperature judgment nodes, the target range of the temperature rise duration is reset, and the power ratio of each heat input path is adjusted and optimized. This achieves the linkage reconstruction of the heat input distribution scheme in the temporal and spatial dimensions to adapt to the changing characteristics of the actual temperature rise status during the vulcanization process.

8. The method for producing Ebnite rubber rollers based on intelligent temperature and pressure control according to claim 1, characterized in that, S5 specifically refers to: Based on the temperature acquisition reliability index and thermal response offset of each spatial node in the judgment logic correction result, the temperature change gradient and pressure response gradient in the time series are jointly extracted to construct a set of temperature and pressure characteristic parameters. The temperature and pressure balance coefficient is calculated by weighted fusion method to quantify the degree of change in the coupling relationship between temperature output and pressure response during the heating stage. During the heating phase, the temperature output and pressure response are synchronously compared based on the temperature-pressure balance coefficient. By establishing a synchronization time index table, the dynamic change trajectories of temperature and pressure at each moment are compared. The sliding window algorithm is used to identify the delay alignment point and synchronization offset trend of the temperature-pressure response curve, and generate a temperature-pressure alignment offset curve for judging the thermal-pressure coordination during the heating process. Based on the synchronous offset values ​​of each time period in the temperature and pressure alignment offset curve, an adaptive adjustment algorithm is used to construct a real-time temperature and pressure adjustment strategy. The heat input power distribution and pressure loading rate during the heating stage are dynamically adjusted according to the sampling period. When the temperature and pressure coupling offset exceeds the control tolerance range, the control parameters are corrected in time to achieve synchronous temperature and pressure control and dynamic stable matching during the heating process.

Images