Intelligent regulation and control method, system and equipment for epoxy resin production

Abstract

The invention is suitable for the technical field of epoxy resin production, and particularly relates to an intelligent regulation and control method, system and equipment for epoxy resin production. Obtaining a corresponding emergency operation set according to the response abnormity index; obtaining process associated data during production of the epoxy resin based on the dynamic compound type reaction anomaly indexes; adjusting the emergency operation set according to the working condition data, the historical efficiency data and the recent operation feedback data, and generating regulation and control instruction sequence data; and controlling a production device to perform production regulation and control on the epoxy resin according to the regulation and control instruction sequence data. According to the epoxy resin production intelligent regulation and control method provided by the invention, the precise executable instruction chain adaptive to the dynamic abnormality can be generated for the standard emergency operation set of the specific abnormality type, and the conflict between the operation instructions is prevented.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of epoxy resin production, and particularly relates to an intelligent regulation and control method, system and device for epoxy resin production. BACKGROUND

[0002] Epoxy resin is a high molecular compound, and contains two or more epoxy groups in the molecular structure. Epoxy resin has good adhesion, chemical corrosion resistance, insulation and mechanical strength, and is widely used in fields such as coatings, adhesives, composite materials and electronic packaging, for example, metal anticorrosion coating, circuit board packaging and the like. The production of epoxy resin is a process of preparing epoxy resin through chemical synthesis and the like. Bisphenol A and epichlorohydrin are used as main raw materials, and epoxy resin is generated through steps such as polycondensation reaction. In the production process, parameters such as reaction temperature, pressure and raw material ratio are controlled to finally produce epoxy resin.

[0003] In the related art, if a dynamic composite type reaction anomaly occurs in the production process of epoxy resin, a standard emergency operation set for a specific abnormal type cannot generate a precise executable instruction chain that adapts to the dynamic anomaly, so that multiple parameter coupling anomalies occur, resulting in operation instruction conflicts. SUMMARY

[0004] The embodiments of the application provide an intelligent regulation and control method, system and device for epoxy resin production, which can solve the problem of operation instruction conflicts caused by the inability to generate a precise executable instruction chain that adapts to the dynamic anomaly, so that multiple parameter coupling anomalies occur.

[0005] In a first aspect, the embodiments of the application provide an intelligent regulation and control method for epoxy resin production, comprising: real-time acquisition of a dynamic composite type reaction anomaly index during epoxy resin production; wherein the reaction anomaly index is used to indicate the deviation degree of the process parameters in the epoxy resin production process from the normal range; obtaining a corresponding emergency operation set according to the reaction anomaly index; wherein the emergency operation set is used to indicate a set of standard operation steps for a specific abnormal type when the production index reaches a preset value; obtaining process correlation data during the production of the epoxy resin based on the dynamic composite type reaction anomaly index; wherein the process correlation data includes working condition data, historical efficiency data and recent operation feedback data; adjust the emergency operation set according to the working condition data, the historical performance data and the recent operation feedback data, and generate regulation and control instruction sequence data; wherein the working condition data is used to reflect the current production stage of the current production line, the current batch of raw materials or the version of the formula and the equipment running state; the historical performance data is used to indicate the change of the quality index and the production stability index of the product obtained after the regulation and control operation is performed under similar working conditions; the operation feedback data is used to indicate the regulation and control operation performed in a short time window before the current abnormal event occurs and the effect feedback; and the regulation and control instruction sequence data is used to indicate the executable instruction chain generated after multi-objective optimization. According to the regulation and control instruction sequence data, the production device is controlled to produce and regulate the epoxy resin.

[0006] The epoxy resin production intelligent regulation and control method provided in the application can obtain dynamic composite reaction abnormality indexes in real time during epoxy resin production, can identify dynamic abnormalities in the production process, can obtain corresponding emergency operation sets according to the reaction abnormality indexes, can obtain process correlation data during epoxy resin production based on the dynamic composite reaction abnormality indexes, can adjust the emergency operation set according to working condition data, historical performance data and recent operation feedback data, can generate regulation and control instruction sequence data, and can control the production device to produce and regulate the epoxy resin according to the regulation and control instruction sequence data. When a dynamic composite reaction abnormality occurs, a precise executable instruction chain that adapts to the dynamic abnormality can be generated for a standard emergency operation set of a specific abnormal type, operation instruction conflicts caused by multi-parameter coupling abnormalities can be prevented, and conflicts between operation instructions can be prevented.

[0007] In a second aspect, the embodiments of the application provide an epoxy resin production intelligent regulation and control system, which comprises: real-time acquisition of dynamic composite reaction abnormality indexes during epoxy resin production; wherein the reaction abnormality indexes are used to indicate the deviation degree of the process parameters in the epoxy resin production process from the normal range; obtaining corresponding emergency operation sets according to the reaction abnormality indexes; wherein the emergency operation set is used to indicate that when the production index reaches a preset value, a standard operation step set for a specific abnormal type is used; obtaining process correlation data during the epoxy resin production based on the dynamic composite reaction abnormality indexes; wherein the process correlation data comprises working condition data, historical performance data and recent operation feedback data; The emergency operation set is adjusted according to the working condition data, the historical performance data and recent operation feedback data, and a regulation and control instruction sequence data is generated; wherein, the working condition data is used to reflect a current production stage of a current production line, a current batch of raw materials or a version of a formula and a device running state; the historical performance data is used to indicate changes of a quality index and a production stability index of a product obtained after a regulation and control operation is performed under a similar working condition; the operation feedback data is used to indicate a regulation and control operation performed in a short time window before the current abnormal event occurs and effect feedback; and the regulation and control instruction sequence data is used to indicate an executable instruction chain generated after multi-target optimization. The production device is controlled according to the regulation and control instruction sequence data to produce and regulate and control the epoxy resin.

[0008] In a third aspect, an embodiment of the present application provides an epoxy resin production intelligent regulation and control device, which comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, and the computer program, when executed by the processor, implements the method in any one of the above first aspect.

[0009] In a fourth aspect, an embodiment of the present application provides a computer program product, which, when executed on an epoxy resin production intelligent regulation and control device, causes the epoxy resin production intelligent regulation and control device to perform the epoxy resin production intelligent regulation and control method in any one of the above first aspect.

[0010] It can be understood that the beneficial effects of the above-mentioned second aspect to fourth aspect can be referred to the related description in the above-mentioned first aspect, which will not be repeated here. BRIEF DESCRIPTION OF DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of these drawings.

[0012] Figure 1 is a flowchart of an epoxy resin production intelligent regulation and control method provided by an embodiment of the present application; Figure 2 is an implementation flowchart of step S100 in the epoxy resin production intelligent regulation and control method provided by an embodiment of the present application; Figure 3 is an implementation flowchart of step S200 in the epoxy resin production intelligent regulation and control method provided by an embodiment of the present application; Figure 4is a flowchart of implementation of step S300 in the intelligent control method for epoxy resin production provided by an embodiment of the present application; Figure 5 is a flowchart of implementation of step S330 in the intelligent control method for epoxy resin production provided by an embodiment of the present application; Figure 6 is a flowchart of implementation of step S400 in the intelligent control method for epoxy resin production provided by an embodiment of the present application; Figure 7 is a flowchart of implementation of step S420 in the intelligent control method for epoxy resin production provided by an embodiment of the present application; Figure 8 is a flowchart of implementation of step S423 in the intelligent control method for epoxy resin production provided by an embodiment of the present application; Figure 9 is a structural diagram of the intelligent control system for epoxy resin production provided by an embodiment of the present application; Figure 10 is a structural diagram of the control device of the intelligent control equipment for epoxy resin production provided by an embodiment of the present application. DETAILED DESCRIPTION

[0013] In the following description, specific details are set forth, such as a particular system architecture, techniques, etc., in order to provide a thorough understanding of the embodiments of the present application. However, persons skilled in the art will understand that the present application can be implemented in other embodiments without these specific details. In other instances, well-known systems, devices, circuits, and methods have not been described in detail so as not to unnecessarily obscure the description of the present application.

[0014] It should be understood that, when used in the specification and the appended claims of the present application, the term "comprising" indicates the presence of the described features, integers, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0015] It should also be understood that the term "and / or" used in the specification and the appended claims of the present application means any combination of one or more of the associated listed items and all possible combinations, and includes these combinations.

[0016] As used in the specification and the appended claims, the term “if’ can be interpreted as meaning “when,” or “as soon as” or “in response to a determination” or “in response to a detection” depending on the context. Similarly, the phrase “if it is determined” or “if [the described condition or event] is detected” can be interpreted as meaning “as soon as it is determined” or “in response to the determination” or “as soon as [the described condition or event] is detected” or “in response to the detection of [the described condition or event]” depending on the context.

[0017] In addition, in the description of the present application and the appended claims, the terms “first”, “second”, “third”, etc. are only used to distinguish the description, and cannot be understood as indicating or implying relative importance.

[0018] Reference in the specification to “one embodiment” or “some embodiments” means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the application. The appearances of the phrases “in one embodiment”, “in some embodiments”, “in other embodiments”, “in additional embodiments”, etc. in various places in the specification are not necessarily all referring to the same embodiment, although they can. The terms “comprising”, “including”, “having” and their variants mean “including but not limited to”, unless otherwise expressly specified and are to be interpreted in the manner as set forth in the section “Definition of Open Terms” of this disclosure.

[0019] In the related art, during the production process of epoxy resin, dynamic composite reaction anomaly refers to the simultaneous deviation of multiple process parameters such as temperature, pressure, flow, reaction time, etc. from the established normal range during the production of epoxy resin, and the degree of deviation changes dynamically with the progress of the production process. If a dynamic composite reaction anomaly occurs (i.e. multiple process parameters deviate from the normal range and the degree of deviation changes dynamically with the production process), the production system needs to be able to quickly identify the type of anomaly and generate a standard emergency operation set. This set of operations should be able to provide a precise and executable instruction chain for a specific type of anomaly to guide the automated system to take appropriate measures to adjust the production process and return the process parameters to the normal range. However, the existing emergency operation set cannot adapt to such dynamically changing abnormal conditions, and the existing standard emergency operation set for a single type of anomaly does not consider the multi-parameter coupling relationship and dynamic change characteristics, resulting in direct conflicts or implicit interference between operation instructions, which cannot generate precise control instruction chains that adapt to real-time abnormal states, and may lead to multi-parameter coupling anomalies, and further cause conflicts between operation instructions.

[0020] To solve the above problems, the embodiment of the present application provides an epoxy resin production intelligent regulation method, system and device. In the method, the epoxy resin production intelligent regulation method provided by the present application can realize the identification of dynamic abnormalities in the production process by acquiring the dynamic composite reaction abnormal index in real time during the production of epoxy resin. The corresponding emergency operation set is obtained according to the reaction abnormal index, the process correlation data during the production of epoxy resin is obtained based on the dynamic composite reaction abnormal index, and the emergency operation set is adjusted according to the working condition data, historical efficiency data and recent operation feedback data to generate a regulation instruction sequence data. The production device is controlled to produce and regulate the epoxy resin according to the regulation instruction sequence data. That is, when a dynamic composite reaction abnormality occurs, a precise executable instruction chain that adapts to the dynamic abnormality can be generated for the standard emergency operation set of a specific abnormal type, preventing the operation instruction conflict caused by multi-parameter coupling abnormality, and further preventing the conflict between operation instructions.

[0021] The epoxy resin production intelligent regulation method provided by the embodiment of the present application can be applied to an epoxy resin production intelligent regulation device. At this time, the epoxy resin production intelligent regulation device is the execution subject of the epoxy resin production intelligent regulation method provided by the embodiment of the present application. The specific type of the epoxy resin production intelligent regulation device is not limited in the embodiment of the present application.

[0022] For example, the epoxy resin production intelligent regulation device includes a production device and a control device. The production device and the control device are in communication connection. The production device can include a phenolic resin reaction kettle, a raw material conveying pump, a temperature controller and a pressure sensor, etc. The phenolic resin reaction kettle is the core equipment of production, which is used for polycondensation reaction to generate epoxy resin. The raw material conveying pump is responsible for conveying raw materials such as phenol A and epichlorohydrin into the reaction kettle in proportion. The temperature controller and the pressure sensor monitor the temperature and pressure parameters in the reaction process in real time, so that they fluctuate within the preset range. The control device can be a mobile phone, a tablet computer, a notebook computer, a netbook, a desktop computer, a smart large screen, a smart television, a computer, a laptop computer, a handheld computing device, etc., but is not limited thereto.

[0023] In order to better understand the epoxy resin production intelligent regulation method provided by the embodiment of the present application, the specific implementation process of the epoxy resin production intelligent regulation method provided by the embodiment of the present application is exemplarily introduced as follows.

[0024] Figure 1 The schematic flowchart of the epoxy resin production intelligent regulation method provided by the embodiment of the present application is shown. The epoxy resin production intelligent regulation method includes: S100, acquiring a dynamic composite reaction abnormality index of the epoxy resin production in real time; wherein the reaction abnormality index is used to indicate the deviation degree of the process parameter in the epoxy resin production process from the normal range.

[0025] It can be understood that the dynamic composite reaction abnormality index includes a main index and a secondary index; wherein the main index is a viscosity mutation gradient (Δη / Δt>15% / min), a thermal accumulation imbalance degree (an axial temperature difference greater than 8℃), and an epoxy group attenuation deviation degree (|Δepoxy value|>0.02 eq / 100g); and the secondary index is a by-product concentration change rate and a molecular weight distribution width index fluctuation (ΔPDI greater than 0.3).

[0026] Exemplarily, the acquisition of the dynamic composite reaction abnormality index of the epoxy resin production can be achieved by setting multiple sensors on the production line. For example, a viscosity sensor can monitor the viscosity change of the epoxy resin in real time, and a temperature sensor and a pressure sensor can monitor the temperature and pressure in the reaction kettle, so as to calculate the thermal accumulation imbalance degree.

[0027] In a possible implementation, referring to Figure 2 , S100, acquiring a dynamic composite reaction abnormality index of the epoxy resin production in real time, including: S110, in the case of epoxy resin production and in the polycondensation reaction stage, monitoring the viscosity change rate.

[0028] It can be understood that the relative change amount of the viscosity value of the epoxy resin per unit time (% / min) reflects the kinetic state of the molecular chain growth in the polycondensation reaction.

[0029] Exemplarily, in the polycondensation reaction stage, a high-precision viscosity online monitoring instrument (such as a rotary viscometer adapted to the sampling circuit of the reaction kettle and installed on the outlet pipe of the reaction kettle) is set to monitor the frequency, for example, to collect viscosity data once every 1 minute, and then to subtract the viscosity value of the previous time from the viscosity value of the next time, and then to divide the time interval between the two times to obtain the viscosity change rate in this time period. The viscosity change rate data in this stage is continuously monitored and recorded.

[0030] S120, determining the heat release acceleration according to the viscosity change rate; wherein the heat release acceleration is used to reflect the change of the heat release rate of the epoxy resin in the polycondensation reaction process.

[0031] It can be understood that the heat release acceleration is the change amount of the heat release rate per unit time (J / (kg·s²)), which represents the reaction intensity.

[0032] Exemplarily, the heat release acceleration can be determined by converting the viscosity change rate to the heat release rate, which can be obtained according to the formula: the heat release rate is proportional to (Δη / Δt), and then the change amount of the heat release rate is calculated: that is, the heat release rate at the continuous time point is differentiated, and the heat release acceleration can be obtained.

[0033] S130, when the viscosity change rate is greater than the first condition and the heat release acceleration is greater than the second condition, an abnormal index of molecular chain rupture risk is obtained.

[0034] It can be understood that the abnormal index of molecular chain rupture risk is a quantitative value (for example, an index between 0 and 1), which represents the probability of the molecular chain of the epoxy resin being broken in the polycondensation reaction. The first condition (for example, the viscosity change rate is greater than 1.8 Pa·s / s) and the second condition (for example, the heat release acceleration is greater than 4 J / s²) are threshold values set based on experimental data, which reflect that the reaction is too violent and may cause chain rupture.

[0035] Exemplarily, the viscosity change rate and the heat release acceleration are compared with the preset conditions, the first condition is set as a threshold value A (for example, 1.8 Pa·s / s), and the second condition is set as a threshold value B (for example, 4 J / s²). When both are greater than the threshold value, the index is calculated: the index is f(Δη / Δt, d²Q / dt²), wherein f is a linear or nonlinear function (for example, the index = w1×(Δη / Δt) + w2×(d²Q / dt²), and the weights w1 and w2 can be obtained by machine learning training), and after calculation, the index value is stored as a database record (for example, greater than 0.7 indicates a high risk). For example, if Δη / Δt = 2.0 Pa·s / s > A and d²Q / dt² = 5 J / s² > B, then the index = 0.8, and the abnormal index of molecular chain rupture risk can be obtained.

[0036] S140, obtaining a reaction abnormality index according to the abnormal index of molecular chain rupture risk.

[0037] Exemplarily, according to the abnormal index of molecular chain rupture risk (for example, a value X), and in combination with sensor data (for example, real-time readings of temperature sensors and pressure sensors), a weighted summation method is used: reaction abnormality index = α×X + β×T_dev + γ×P_dev, wherein α, β, and γ are weight coefficients, T_dev is a temperature deviation (current temperature-target temperature), and P_dev is a pressure deviation. After calculation, the index value is normalized to the range of 0-100. For example, if X = 0.8, T_dev = 5°C, P_dev = 0.2 bar, and α = 0.6, β = 0.3, and γ = 0.1, then the index = 0.60.8 + 0.35 + 0.1*0.2 = 48.2 (after normalization, about 48), and the reaction abnormality index can be obtained to indicate the degree of deviation of the process parameters in the epoxy resin production process from the normal range.

[0038] In this way, by integrating multi-source data to generate a reaction abnormality index, an overall process view is provided, quick decision-making is facilitated, single parameter misguidance is avoided, and the systematicness and reliability of abnormality management are enhanced.

[0039] S200, obtaining a corresponding emergency operation set according to the reaction abnormality index; wherein the emergency operation set is used to indicate a set of standard operation steps for a specific abnormality type when the production index reaches a preset value.

[0040] It can be understood that the emergency operation set is a series of predefined operation instructions (such as adjusting the temperature or adding a catalyst) obtained for a specific abnormality type (such as thermal runaway or chain rupture).

[0041] Exemplarily, obtaining the corresponding emergency operation set can be by querying a preset rule base (stored in a database), which maps the reaction abnormality index to an operation template. For example, an index value of 50-70 corresponds to a "moderate risk" template, which includes operation steps such as reducing the reaction kettle temperature by 5 degrees and increasing the stirring speed, as well as the increased speed value, selects and outputs the set. For example, if the index = 55, the set contains the step sequence: set the temperature to reduce by 5 degrees, inject 0.5L of inhibitor.

[0042] In one possible implementation, please refer to Figure 3 S200, obtaining a corresponding emergency operation set according to the reaction abnormality index, comprising: S210, monitoring process parameters in real time, and constructing abnormal parameter system data based on the process parameters; wherein the abnormal parameter system data is used to indicate an abnormal feature tensor.

[0043] It can be understood that the process parameters are temperature, pressure, viscosity, flow, liquid level, stirring speed / power, pH, key component concentration, valve opening, etc. in the production process; the normal parameter system data is a multi-dimensional data structure that integrates multiple parameters to represent abnormal features. The abnormal feature tensor is used to quantify the abnormality strength.

[0044] Exemplarily, the controller reads data from multiple sensors in real time (sampling every second), calculates the deviation of each parameter (current value - set value), and then combines it into a tensor format (for example, tensor T = [ΔT, ΔP, ΔF], where ΔT is the temperature deviation), and the tensor dimension is dynamically adjusted according to the number of parameters.

[0045] S220, activating multi-level matching data based on the abnormal feature tensor indicated by the abnormal parameter system data; wherein the multi-level matching data is used to indicate a set of standard operation steps for a specific abnormality type.

[0046] It can be understood that the multi-level matching data is a data set processed by three levels of analysis methods (pattern recognition, graph reasoning, digital twin) on the abnormal feature tensor. The first level of pattern recognition is to match the current abnormal feature tensor with the historical abnormal pattern library (for example, to identify temperature sudden rise type abnormality); the second level of graph reasoning is to infer the possible operation direction based on the historical abnormal handling effect graph (for example, the influence curve of cooling operation on temperature); and the third level of digital twin simulation is to simulate the effect of different operations through the digital twin model of the reaction kettle.

[0047] Exemplarily, the implementation of activating the multi-level matching data can be that the abnormal feature tensor is input into a matching engine, the tensor is compared with a historical database, a similar pattern index is output, the abnormal root cause (for example, high temperature causes viscosity to rise) is obtained through a pre-built knowledge graph (nodes are parameters and edges are causal relationships), different operation effects (for example, viscosity change after cooling) are predicted through a digital twin model, and the matching data is output as a hierarchical report.

[0048] S230, generating a dynamic operation graph according to the multi-level matching data; wherein the dynamic operation graph is used to indicate a dynamic operation graph generated according to different levels of the abnormal feature tensor.

[0049] Exemplarily, the dynamic operation graph is a visual operation step flowchart, and the steps are dynamically adjusted according to the levels of the abnormal feature tensor (for example, more urgent steps correspond to severe abnormalities). For example, when the first level of pattern recognition matches a severe abnormality, the graph displays an emergency cooling step, the second level of graph reasoning displays a synchronization step of adjusting cooling and stirring, and the third level of simulation verification supplements the step order. For example, based on the multi-level matching data, the dynamic operation graph is generated, that is, the jacket cooling water is opened to the maximum flow (the first level of pattern recognition); the stirring rate is adjusted from 120 rpm to 100 rpm (the second level of graph reasoning, to reduce the stress on the molecular chain), and the bisphenol A feeding is paused for 3 minutes (the third level of simulation, to avoid continuing to heat), the graph is sorted according to the step priority, and the expected effect of each step (for example, the temperature is reduced to 185°C 5 minutes after the first step is executed) is marked.

[0050] S240, obtaining a corresponding emergency operation set according to the dynamic operation graph.

[0051] Exemplarily, the leaf node operation (for example, setting the temperature to 80°C) is extracted through the dynamic operation graph and is serialized into an executable instruction list, and the instruction format is “action-parameter-target value” (for example, SET_TEMP, 80 degrees). The above is single, and a plurality of cases can be combined into the corresponding emergency operation set.

[0052] In this way, the operation set is accurately matched with the abnormality through the atlas conversion, the execution error is reduced, and the dynamic operation atlas is converted into specific device control instructions, and the error and delay of manual conversion are reduced.

[0053] S300, obtaining process correlation data during the production of the epoxy resin based on the dynamic composite reaction abnormality index; wherein the process correlation data includes working condition data, historical efficiency data, and recent operation feedback data.

[0054] It can be understood that the working condition data reflects the current production state (such as raw material batch, equipment state), the historical efficiency data is the processing effect under similar abnormality (such as product molecular weight under past serious abnormality), and the recent operation feedback data is the operation and effect before the abnormality occurs (such as whether the stirring adjustment 10 minutes ago is effective).

[0055] Exemplarily, through the query database, the working condition data comes from real-time sensors (such as the current raw material batch number), the historical efficiency data can be retrieved from the historical database (such as product quality indicators under similar working conditions), and the operation feedback data is extracted from the log (such as operation records in the last 1 hour). The data is integrated into a structured table (such as a SQL table), which can be realized by API calling, and the process correlation data can be obtained.

[0056] In one possible implementation, please refer to Figure 4 S300, obtaining process correlation data during the production of the epoxy resin based on the dynamic composite reaction abnormality index, including: S310, obtaining a deviation degree by using multi-sensor fusion calculation based on the dynamic composite reaction abnormality index.

[0057] Exemplarily, the multi-sensor includes a temperature sensor, a pressure sensor, a viscometer, a vibration sensor, etc.; the fusion calculation is to compare the measurement values of each sensor with the standard value (set value), and to calculate the comprehensive deviation degree (dimensionless, range 0-1, the greater the value, the more serious the deviation) by weighted average method, and the deviation degree is used to quantify the overall deviation of the current process parameter from the normal state. The deviation degree can be obtained by using multi-sensor (temperature, pressure, etc.) data, through the deviation degree formula, deviation degree = w x |abnormality index-normal threshold value|, wherein w is the weight (determined by the sensor accuracy), and the deviation degree can be obtained.

[0058] S320, dynamically generating a double-threshold time window according to the deviation degree; wherein the double-threshold time window is represented as T1, T2.

[0059] It can be understood that the double-threshold time window is based on two time thresholds set according to the deviation degree, T1 is a pre-warning window (allowed reaction adjustment time when the deviation degree is small), and T2 is an emergency window (time that must be completed when the deviation degree is large), the larger the deviation degree, the shorter T1 and T2.

[0060] Exemplarily, the double-threshold time window can be dynamically calculated according to the deviation degree value: T1 = k1 x deviation degree, T2 = k2 x deviation degree (k1 and k2 are coefficients, calibrated by experiment).

[0061] S330, constructing a health attenuation matrix based on the double-threshold time window; wherein the health attenuation matrix is used to indicate the trend of the health state changing over time.

[0062] Exemplarily, the health attenuation matrix is a two-dimensional table, the rows represent time (with T1 and T2 as nodes), the columns represent the health indicators of the device / reaction (such as the heat transfer efficiency of the reaction kettle, the output power of the stirring motor), and the cell value is the health degree 0-1, the smaller the value, the worse the health), used to reflect the attenuation trend of the health state over time (the attenuation accelerates after exceeding T1).

[0063] In one possible implementation, please refer to Figure 5 , after S330, constructing a health attenuation matrix based on the double-threshold time window, comprising: S3301, obtaining the running state of the production device of the epoxy resin; wherein the running state is used to indicate that the current production device is in a normal, pre-warning or fault state.

[0064] It can be understood that the production device includes but is not limited to a reaction kettle, a stirring motor, a cooling water pump, etc. The running state is a categorical variable (normal / pre-warning / fault), and the device health is determined based on sensor data.

[0065] The specific implementation of the running state is that the controller reads the device sensor (such as a vibration sensor and a thermometer), if the parameter is within the normal range, the state = normal; if it exceeds the pre-warning threshold, the state = pre-warning; if it exceeds the fault threshold, the state = fault. For example, if the vibration value > 5mm / s, it is pre-warning.

[0066] S3302, extracting the device wear index of the production device, and performing device coefficient calculation based on the device wear index to obtain a device coefficient value; wherein the device coefficient value is used to indicate the execution capability of the current production device.

[0067] It can be understood that the equipment wear index includes the corrosion rate of the inner wall of the reaction kettle (mm / year), the wear amount of the stirring paddle (mm), and the wear degree of the valve sealing surface (leakage rate %). The equipment coefficient value is a coefficient calculated based on the comprehensive wear index (0-1, the larger the value, the stronger the execution capability). For example, the coefficient value of a new equipment is approximately 1, and the coefficient value of a severely worn equipment is approximately 0.4.

[0068] Exemplarily, the coefficient is calculated based on the wear data, i.e., the equipment coefficient value = 1-(wear index / maximum allowed wear). For example, if the wear index = 200 hours (maximum = 1000 hours), the coefficient = 0.8, i.e., the coefficient 0.8 can be determined as the equipment coefficient value.

[0069] S3303, obtaining a health attenuation factor of the current production equipment according to the equipment coefficient value and the running state; wherein the health attenuation factor is used to indicate the attenuation degree of the performance of the current production equipment changing with time.

[0070] Exemplarily, the attenuation degree of the performance of the current production equipment changing with time can be represented as a performance decline speed; the health attenuation factor of the current production equipment can be obtained by using time series data, i.e., calculating (initial coefficient-current coefficient) / time interval to obtain the health attenuation factor.

[0071] S3304, determining a corrected operation parameter according to the health attenuation factor of the production equipment.

[0072] Exemplarily, the corrected operation parameter is a parameter adjusted to offset the influence of equipment health attenuation on operation, for example: the health attenuation factor is large, and the opening degree of the cooling valve needs to be increased. The attenuation factor is queried and a preset rule is used (for example, if the factor >0.5% / day, the operation margin is increased). For example, the corrected temperature set value = original set value+k x attenuation factor (k is a compensation coefficient).

[0073] In this way, the equipment attenuation is automatically compensated, the production precision is maintained, the actual ability of the equipment is adapted to the emergency operation, and the reliability of the operation is improved.

[0074] S340, obtaining process correlation data based on the health attenuation matrix.

[0075] Exemplarily, "T1=5 minutes when the heat transfer efficiency of the reaction kettle is 0.7" is extracted from the health attenuation matrix and supplemented to the working condition data, and "T2=10 minutes of historical efficiency data, when the equipment health degree is 0.4, the product qualified rate is 85%" is extracted to obtain process correlation data containing the attenuation trend of the equipment health with time.

[0076] In this way, by deviation, time window, and health attenuation matrix construction, dynamic correlation analysis of abnormal reaction and equipment state is realized, multi-dimensional (time, equipment, reaction) data support is provided for adjustment of emergency operation, and comprehensiveness of correlation data is enhanced.

[0077] S400, adjusting the emergency operation set according to the working condition data, the historical efficiency data, and the recent operation feedback data to generate a regulation instruction sequence data; wherein the working condition data is used to reflect the current production stage of the current production line, the current batch of raw materials or the formula version used, and the equipment running state; the historical efficiency data is used to indicate the change of the quality index and the production stability index of the product obtained after the regulation operation is performed under similar working conditions; the operation feedback data is used to indicate the regulation operation and the effect feedback performed within a short time window before the current abnormal event occurs; and the regulation instruction sequence data is used to indicate the executable instruction chain generated after multi-objective optimization.

[0078] For example, the regulation instruction sequence data is an optimized instruction chain of the initial emergency operation set (for example, "step 1: open the cooling valve → step 2: reduce stirring → step 3: add catalyst"), the optimization is based on the current working condition (for example, the high water content of the raw material needs to be adjusted), the historical effect (for example, the same operation in the past makes the product qualified), and the recent operation feedback (for example, the effect of reducing stirring is poor and needs to be increased), and finally realizes multi-objective (for example, temperature drop and molecular weight standard).

[0079] In one possible implementation, please refer to Figure 6 S400, adjusting the emergency operation set according to the working condition data, the historical efficiency data, and the recent operation feedback data to generate a regulation instruction sequence data, comprising: S410, performing a preliminary screening operation on the operation feedback data according to the working condition data, the historical efficiency data, and the recent operation feedback data to obtain screening data; wherein the screening data is used to indicate a heat transfer compensation factor of the production equipment.

[0080] It can be understood that the preliminary screening operation is to eliminate the operation feedback data irrelevant to the current abnormality (for example, irrelevant operation 1 hour ago) and retain the key data (for example, temperature adjustment feedback in the last 30 minutes); and the heat transfer compensation factor is a coefficient used to correct the heat transfer efficiency of the equipment.

[0081] For example, obtaining the screening data can be by extracting the raw material data (for example, water content of bisphenol A), calculating the preliminary screening data (for example, correction amount), combining the equipment state (for example, vibration value) to calculate the output heat transfer compensation factor, for example, the factor is f (water content, vibration value), so that the screening data focuses on the key heat transfer compensation information, and provides a basis for subsequent operation parameter adjustment, and reduces the situation of insufficient cooling or heating due to the decrease of the heat transfer efficiency of the equipment.

[0082] In a possible implementation, S410, the working condition data, the historical efficiency data and the recent operation feedback data are subjected to a preliminary screening operation to obtain screening data, including: S411, the water content of the current batch of bisphenol A and the purity of epichlorohydrin are extracted.

[0083] Exemplarily, the extraction manner can be extracting data through a raw material detection report, reading raw material batch data from a database or a sensor.

[0084] S412, the preliminary screening data are calculated based on the water content of bisphenol A and the purity of epichlorohydrin; wherein the preliminary screening data are used to indicate the correction amount of the basic operation.

[0085] Exemplarily, the correction amount is an adjustment value of the operation parameter, that is, the preliminary screening data are operation correction amounts calculated according to the purity and water content of the raw material. The formula can be expressed as: basic operation correction amount = (actual water content / standard water content-1) x k1 + (1-actual purity / standard purity) x k2 (k1, k2 are coefficients).

[0086] S413, the bearing vibration value of the stirrer and the sealing leakage rate are obtained to obtain the equipment state compensation coefficient.

[0087] Exemplarily, the bearing vibration value (mm / s) of the stirrer reflects the degree of bearing wear, and large vibration indicates poor stirring stability; the sealing leakage rate (%) reflects the sealing performance of the stirring shaft, and high leakage rate indicates possible air / liquid leakage; the equipment state compensation coefficient is a comprehensive correction coefficient of the two (0-1.2, the larger the value, the greater the adjustment range). The equipment state compensation coefficient can be calculated by reading the vibration sensor and the leakage detector data to calculate the coefficient as 1-(vibration value / maximum vibration)-(leakage rate / maximum leakage); for example, the vibration value = 4 mm / s (maximum = 10), the leakage rate = 0.1% (maximum = 0.5%), and the coefficient = 0.86.

[0088] S414, the screening data are obtained by analyzing the correction amount of the basic operation and the equipment state compensation coefficient and the historical efficiency data.

[0089] Exemplarily, in combination with the basic operation correction amount (for example, cooling flow + 3.27 m³ / h), the equipment state compensation coefficient (for example, 1.125), and the historical performance data (for example, heat transfer effect under the same correction in the past), the screening data (heat transfer compensation factor) is determined, and the formula can be expressed as: heat transfer compensation factor = basic operation correction amount x equipment state compensation coefficient x historical effect coefficient. For example, the basic operation correction amount = 3.27 m³ / h, the equipment state compensation coefficient = 1.125, and the historical effect coefficient under the same condition in the historical performance data = 0.9 (because the actual effect in the historical operation is slightly lower than the theoretical value). The calculation of the screening data (heat transfer compensation factor) = 3.27 x 1.125 x 0.9 ≈ 3.34, that is, the final cooling flow needs to be increased by 3.34 m³ / h to compensate for the heat transfer loss.

[0090] In this way, the screening data comprehensively considers the influences of raw materials, equipment, and historical effects, accurately quantifies the heat transfer compensation demand, provides accurate correction basis for subsequent temperature control, gradually focuses on key heat transfer compensation information, so that the screening data can accurately reflect the heat transfer demand of the equipment and provide a reliable basis for subsequent operation strengthening.

[0091] S420, based on the screening data, the operation feedback data is subjected to strengthening operation to obtain strengthening data; wherein the strengthening data is used to indicate the dynamic operation performance index of the production equipment.

[0092] It can be understood that the strengthening operation is a weighted processing of the operation feedback data after the preliminary screening, and highlights the effective operation; the dynamic operation performance index is an index quantifying the operation effect, and the larger the index value is, the higher the performance is.

[0093] Exemplarily, the screening data is input, and a weighted update calculation index is applied, that is, the index is obtained by multiplying the historical performance by the screening data factor. For example, if the historical performance = 0.9 and the factor = 0.58, then the index = 0.9 x 0.58 = 0.522, that is, 0.522 is the dynamic operation performance index of the production equipment indicated by the strengthening data.

[0094] In one possible implementation, please refer to Figure 7 , after S420, based on the screening data, the operation feedback data is subjected to strengthening operation to obtain strengthening data, comprising: S4201, selecting a historical operation item whose dynamic operation performance index indicated by the strengthening data meets the first index requirement; wherein meeting the first index requirement means being greater than or equal to the index 0.85.

[0095] It can be understood that the historical operation item is a record of past operation that has been performed and has good effect, and the purpose of selecting the operation item is to extract an effective regulation strategy therefrom to cope with the current production anomaly. By comparing the dynamic operation effectiveness index with a preset first index requirement (for example, 0.85), records with high effectiveness in the historical operation are screened out to provide a reference for subsequent generation of regulation instruction sequence data.

[0096] Exemplarily, the historical operation item with the dynamic operation effectiveness index indicated by the selected reinforcement data meeting the first index requirement can be an operation record (for example, a cooling operation) with an index greater than or equal to 0.85, which is retrieved by querying a historical database and output as a candidate list.

[0097] S4202, replacing operation items in the emergency operation set meeting the second index requirement according to priority; wherein the second index requirement is less than or equal to 0.6.

[0098] It can be understood that the replacement according to priority is to replace operation items with low effectiveness (index less than 0.6) in the emergency operation set with operation items with high effectiveness in the candidate list by evaluating the priority of the historical operation item (for example, based on operation difficulty, execution time, required resources, and the like).

[0099] Exemplarily, if the emergency operation set contains a cooling operation with a dynamic operation effectiveness index of 0.55 (less than 0.6), a historical cooling operation (for example, using different cooling medium or adjusting the opening degree of the cooling valve) with a dynamic operation effectiveness index of 0.92 can be selected from the candidate list to replace the original cooling operation. In this way, it can be ensured that each operation in the emergency operation set has high effectiveness, thereby improving the ability to cope with production anomalies.

[0100] S4203, in the case of being in the polycondensation reaction stage, injecting a catalyst supplement rule, and if the efficiency of the tertiary amine catalyst decreases by more than 15%, a pre-activation instruction is added.

[0101] Exemplarily, the purpose of the added pre-activation instruction is to compensate for the influence of the decrease in catalyst efficiency on the reaction rate. The pre-activation instruction can include increasing the catalyst concentration, adjusting the catalyst injection rate, or using other pre-activation techniques to enable the polycondensation reaction to continue efficiently, to flexibly cope with changes in catalyst efficiency and maintain the stability and efficiency of the production process. If the efficiency of the tertiary amine catalyst decreases by more than 15%, the pre-activation instruction can be added by monitoring the catalyst efficiency (for example, the reaction rate ratio), and if it decreases by more than 15% (for example, from 100% to 84%), the instruction to pre-activate the catalyst and heat it to 50 degrees for 5 minutes is inserted into the operation sequence.

[0102] S4204, if sodium salt catalyst residue is detected, a neutralization treatment instruction is inserted.

[0103] Exemplarily, the neutralization instruction is a chemical treatment command, and the implementation of the insertion instruction is: by detecting sodium salt (for example, the concentration >0.1%) through the residual sensor, the injection instruction of adding a neutralizing agent, acetic acid 0.2L, is added to the sequence, so as to make the emergency operation set more perfect and efficient by screening high-efficiency operations, replacing low-efficiency operations, and supplementing special scene instructions (catalyst activation, neutralization), and adapting to the complex abnormal scene of polycondensation reaction.

[0104] S423, obtaining regulation instruction sequence data according to the heat transfer compensation factor indicated by the screening data and the dynamic operation efficiency index indicated by the strengthening data.

[0105] Exemplarily, obtaining regulation instruction sequence data can be to combine the heat transfer compensation factor and the dynamic operation efficiency index, arrange the operation steps in time sequence and priority, and form an executable regulation instruction sequence.

[0106] In a possible implementation, please refer to Figure 8 S423, obtaining regulation instruction sequence data according to the heat transfer compensation factor indicated by the screening data and the dynamic operation efficiency index indicated by the strengthening data, including: S4231, calculating a temperature control reference value according to the heat transfer compensation factor indicated by the screening data.

[0107] Exemplarily, the temperature control reference value is a target temperature corrected based on the heat transfer compensation factor, and the formula can be expressed as: reference value = set temperature + (heat transfer compensation factor × correction coefficient); for example, the set temperature is 180℃, the heat transfer compensation factor is 3.34, and the correction coefficient is 0.5℃ / unit compensation factor, and the calculated temperature control reference value = 180- (3.34 × 0.5) = 180-1.67≈178.3℃, that is, the temperature control reference value is obtained.

[0108] S4232, obtaining a temperature correction instruction set based on the temperature control reference value.

[0109] It can be understood that the temperature correction instruction set is a series of operation instructions according to the temperature control reference value.

[0110] Exemplarily, the temperature correction instruction set can include operations such as adjusting the flow of cooling medium, heating power or stirring rate, and is comprehensively analyzed according to the current working condition, equipment state and historical efficiency data. For example, if the temperature deviates from the upper limit of the reference value, the instruction of increasing the flow of cooling medium is issued; if the temperature is low, the instruction of increasing the heating power is issued. By continuously monitoring the temperature and dynamically adjusting the instruction set, the temperature control in the production process is always in the optimal state, so as to guarantee the production quality and efficiency of the epoxy resin.

[0111] S4233, constructing an operation priority queue according to the dynamic operation performance index indicated by the reinforcement data, and obtaining a reconstructed operation sequence based on the operation priority queue.

[0112] It can be understood that the operation priority queue is a list of operation items sorted according to the dynamic operation performance index, and the operation item with a higher performance index has a higher priority. The reconstructed operation sequence is to rearrange the operation items in the original emergency operation set according to the order of the operation priority queue, so that the operation with high performance can be executed first when executed.

[0113] For example, if the dynamic operation performance index indicated by the reinforcement data shows that the performance of a certain operation is extremely high (for example, 0.95), it will be placed at the top of the operation priority queue and executed first to quickly adjust the production state and improve the stability of the production process and the quality of the product, so that the operation items in the emergency operation set are executed in order according to the performance, and the overall control effect is improved.

[0114] S4234, obtaining a control instruction sequence data according to the temperature correction instruction set and the reconstructed operation sequence.

[0115] For example, the temperature correction instruction set and the reconstructed operation sequence are integrated to form a control instruction chain containing time nodes, device parameters, and expected effects, and then instructions are sent according to the control instruction chain, which can be directly executed by the device.

[0116] In this way, through automation execution, rapid and accurate production control is realized, the abnormal influence is minimized, the quality and efficiency of epoxy resin production are improved, and through temperature correction, priority sorting, and sequence reconstruction, the finally generated control instruction sequence data realizes multi-objective optimization of emergency operation, i.e. temperature stability, normal growth of molecular chain, and product quality meeting standards.

[0117] S500, controlling the production device to produce and control the epoxy resin according to the control instruction sequence data.

[0118] For example, the production device includes the cooling system of the reaction kettle, the stirring motor, the raw material feeding pump, the catalyst adding device, etc.; the control device converts the control instruction sequence data into signals (such as electric valve opening degree, motor frequency) recognizable by each device, automatically controls the device to execute the operation, and realizes real-time control of the polycondensation reaction.

[0119] In summary, when a dynamic composite reaction anomaly occurs, a precise executable instruction chain that adapts to the dynamic anomaly can be generated for the standard emergency operation set of a specific abnormal type, preventing operation instruction conflicts caused by multi-parameter coupling anomalies, and further preventing conflicts between operation instructions.

[0120] It should be understood that the size of the serial number of each step in the above embodiment 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.

[0121] Corresponding to the intelligent regulation and control method for epoxy resin production described in the above embodiments, the embodiments of the present application also provide an intelligent regulation and control system for epoxy resin production. Each unit of the system can implement each step of the intelligent regulation and control method for epoxy resin production. Figure 9 The structure block diagram of the intelligent regulation and control system for epoxy resin production provided by the embodiments of the present application is shown, and only the parts related to the embodiments of the present application are shown for ease of illustration.

[0122] Reference Figure 9 The intelligent regulation and control system for epoxy resin production includes: An acquisition unit is configured to acquire a dynamic composite reaction abnormality index in real time during epoxy resin production. The reaction abnormality index is used to indicate the deviation of the process parameters in the epoxy resin production process from the normal range. A first obtaining unit is configured to obtain a corresponding emergency operation set according to the reaction abnormality index. The emergency operation set is used to indicate a set of standard operation steps for a specific abnormality type when it is monitored that the production index reaches a preset value. A second obtaining unit is configured to obtain process correlation data during epoxy resin production based on the dynamic composite reaction abnormality index. The process correlation data includes operating condition data, historical efficiency data, and recent operation feedback data. A generation unit is configured to adjust the emergency operation set according to the operating condition data, the historical efficiency data, and the recent operation feedback data, and generate a regulation instruction sequence data. The operating condition data is used to reflect the current production stage of the current production line, the current batch of raw materials or the formula version used, and the equipment running state. The historical efficiency data is used to indicate the change of the quality index and the production stability index of the product obtained after the control operation is performed under similar operating conditions. The operation feedback data is used to indicate the control operation and effect feedback performed within a short time window before the current abnormal event occurs. The regulation instruction sequence data is used to indicate an executable instruction chain generated after multi-objective optimization. A result unit is configured to control the production device to produce and regulate the epoxy resin according to the regulation instruction sequence data.

[0123] It should be noted that the information interaction, execution process, etc. between the above-mentioned systems / units, since based on the same concept as the method embodiments of the present application, the specific functions and the technical effects brought by them can be referred to the method embodiments part, which will not be repeated here.

[0124] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0125] This application also provides an intelligent control device for epoxy resin production. Figure 10 This is a schematic diagram of the structure of a control device provided in an embodiment of this application. Figure 10 As shown, the control device 6 in this embodiment includes: at least one processor 60 ( Figure 10 Only one is shown in the image), at least one memory 61 ( Figure 10 (Only one is shown in the image) and a computer program 62 stored in the at least one memory 61 and executable on the at least one processor 60. When the processor 60 executes the computer program 62, it causes the control device 6 to perform the steps in any of the above embodiments of the intelligent control method for epoxy resin production, or causes the control device 6 to perform the functions of each module / unit in the above embodiments of the system.

[0126] For example, the computer program 62 may be divided into one or more modules / units, which are stored in the memory 61 and executed by the processor 60 to complete this application. The one or more modules / units may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program 62 in the control device 6.

[0127] The control device 6 can be a desktop computer, laptop, or other computing device. This control device may include, but is not limited to, a processor 60 and a memory 61. Those skilled in the art will understand that... Figure 10 This is merely an example of control device 6 and does not constitute a limitation on control device 6. It may include more or fewer components than shown, or combine certain components, or different components, such as input / output devices, network access devices, buses, etc.

[0128] The processor 60 can be a central processing unit (CPU), and can also be other general-purpose processors, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0129] The memory 61 can be an internal storage unit of the control device 6 in some embodiments, for example, a hard disk or a memory of the control device 6. The memory 61 can also be an external storage device of the control device 6 in other embodiments, for example, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. Further, the memory 61 can include both an internal storage unit and an external storage device of the control device 6. The memory 61 is used to store an operating system, an application program, a boot loader, data, and other programs, for example, program codes of the computer program, etc. The memory 61 can also be used to temporarily store data that has been output or will be output.

[0130] The embodiments of the present application further provide a computer readable storage medium, which stores a computer program. The computer program is executed by a processor to implement the steps in any of the above method embodiments.

[0131] The embodiments of the present application provide a computer program product. When the computer program product is run on an epoxy resin production intelligent control device, the epoxy resin production intelligent control device implements the steps in any of the above method embodiments.

[0132] The integrated unit, if implemented in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, the present application can implement all or part of the processes in the above-mentioned embodiment methods through a computer program to instruct the relevant hardware to complete, and the computer program can be stored in a computer readable storage medium. When the processor executes the computer program, the steps of each method embodiment described above can be implemented. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or some intermediate forms. The computer readable medium at least includes any entity or device capable of carrying the computer program code to the intelligent control device for epoxy production, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium. For example, U disk, mobile hard disk, magnetic disk or optical disk, etc.

[0133] In the above embodiments, the description of each embodiment has its own focus, and the parts not described or recorded in detail in a certain embodiment can be referred to the related description of other embodiments.

[0134] Those skilled in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized by 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. The skilled person 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.

[0135] In the embodiments provided in the present application, it should be understood that the disclosed epoxy production intelligent control system, device and method can be implemented in other ways. For example, the above-described epoxy production intelligent control system and device embodiments are only schematic, for example, the division of the modules or 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 shown or discussed mutual units can be indirect coupling or communication connection through some interfaces, devices or units, and can be electrical, mechanical or other forms.

[0136] 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 also be distributed to multiple network units. Part or all of the units can be selected to achieve the purpose of the embodiment scheme according to actual needs.

[0137] The above embodiments are only used to illustrate the technical solutions of the present application, but not limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that the technical solutions recorded in the foregoing embodiments can still be modified, or some technical features can be replaced by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. An intelligent control method for epoxy resin production, characterized by, The method comprises the following steps: Real-time acquisition of dynamic composite reaction abnormal index during epoxy resin production; wherein, the reaction abnormal index is used to indicate the deviation degree of the process parameters in the epoxy resin production process from the normal range; According to the reaction abnormal index, a corresponding emergency operation set is obtained; wherein, the emergency operation set is used to indicate that when the production index reaches the preset value, a set of standard operation steps for a specific abnormal type is executed; Based on the dynamic composite reaction abnormal index, process correlation data during the epoxy resin production is obtained; wherein, the process correlation data includes working condition data, historical efficiency data and recent operation feedback data; According to the working condition data, the historical efficiency data and the recent operation feedback data, the emergency operation set is adjusted to generate a control instruction sequence data; wherein, the working condition data is used to reflect the current production stage of the current production line, the current batch of raw materials or the formula version and the equipment running state; the historical efficiency data is used to indicate the change of the quality index and the production stability index of the product after the control operation is executed under similar working conditions; the operation feedback data is used to indicate the control operation and effect feedback executed within a short time window before the current abnormal event occurs; the control instruction sequence data is used to indicate the executable instruction chain generated after multi-objective optimization; According to the control instruction sequence data, the production device is controlled to produce and control the epoxy resin.

2. The method of claim 1, wherein the method comprises: determining the amount of the epoxy resin produced; and adjusting the amount of the epoxy resin produced based on the determined amount of the epoxy resin produced. The real-time acquisition of dynamic composite reaction abnormal index during epoxy resin production comprises: In the case of epoxy resin production and polycondensation reaction stage, the viscosity change rate is monitored; According to the viscosity change rate, the heat release acceleration is determined; wherein, the heat release acceleration is used to reflect the change of the heat release rate of the epoxy resin in the polycondensation reaction process; When the viscosity change rate is greater than the first condition and the heat release acceleration is greater than the second condition, a molecular chain rupture risk abnormal index is obtained; According to the molecular chain rupture risk abnormal index, the reaction abnormal index is obtained.

3. The method of claim 1, wherein the method comprises: determining the amount of the epoxy resin produced; and adjusting the amount of the epoxy resin produced based on the determined amount of the epoxy resin produced. According to the reaction abnormal index, a corresponding emergency operation set is obtained; wherein, the emergency operation set is used to indicate that when the production index reaches the preset value, a set of standard operation steps for a specific abnormal type is executed; Real-time monitoring of the process parameters and construction of abnormal parameter system data based on the process parameters; wherein, the abnormal parameter system data is used to indicate the abnormal feature tensor; Based on the abnormal feature tensor indicated by the abnormal parameter system data, multi-level matching data is activated; wherein, the multi-level matching data is used to indicate the first level pattern recognition, the second level graph reasoning and the third level digital twin simulation; According to the multi-level matching data, a dynamic operation graph is generated; wherein, the dynamic operation graph is used to indicate the dynamic operation graph generated by matching different levels of the abnormal feature tensor; According to the dynamic operation graph, a corresponding emergency operation set is obtained.

4. The method of claim 1, wherein the method comprises: determining the amount of the epoxy resin produced; and adjusting the amount of the epoxy resin produced based on the determined amount of the epoxy resin produced. Based on the dynamic composite reaction abnormal index, process correlation data during the epoxy resin production is obtained; wherein, the process correlation data includes working condition data, historical efficiency data and recent operation feedback data; According to the dynamic composite reaction abnormal index, multi-sensor fusion calculation is performed to obtain the deviation degree; According to the deviation, a double-threshold time window is dynamically generated; wherein the double-threshold time window is represented as T1, T2; A health attenuation matrix is constructed based on the double-threshold time window; wherein the health attenuation matrix is used to indicate the trend of the health state changing over time; The process correlation data is obtained based on the health attenuation matrix.

5. The method of claim 4, wherein the control signal is a signal for controlling the temperature of the reactor. After the health attenuation matrix is constructed based on the double-threshold time window, the following steps are included: An operating state of the production equipment of the epoxy resin is obtained; wherein the operating state is used to indicate that the current production equipment is in a normal, pre-warning or fault state; An equipment wear index of the production equipment is extracted, and an equipment coefficient is calculated based on the equipment wear index to obtain an equipment coefficient value; wherein the equipment coefficient value is used to indicate the execution capability of the current production equipment; A health attenuation factor of the current production equipment is obtained according to the equipment coefficient value and the operating state; wherein the health attenuation factor is used to indicate the attenuation degree of the performance of the current production equipment changing over time; A corrected operation parameter is determined according to the health attenuation factor of the production equipment.

6. The method of claim 1, wherein the method comprises: determining the amount of the epoxy resin produced; and adjusting the amount of the epoxy resin produced based on the determined amount of the epoxy resin produced. The following steps are included for adjusting the emergency operation set according to the working condition data, historical efficiency data and recent operation feedback data, generating a control instruction sequence data: The working condition data, the historical efficiency data and the recent operation feedback data are subjected to a preliminary screening operation on the operation feedback data to obtain screening data; wherein the screening data is used to indicate a heat transfer compensation factor of the production equipment; The operation feedback data is subjected to a strengthening operation based on the screening data to obtain strengthening data; wherein the strengthening data is used to indicate a dynamic operation efficiency index of the production equipment; The control instruction sequence data is obtained according to the heat transfer compensation factor indicated by the screening data and the dynamic operation efficiency index indicated by the strengthening data.

7. The intelligent control method for epoxy resin production as described in claim 6, characterized in that, The following steps are included for the preliminary screening operation on the operation feedback data to obtain screening data: The water content of bisphenol A and the purity of epichlorohydrin of the current raw material batch are extracted; The preliminary screening data is calculated based on the water content of bisphenol A and the purity of epichlorohydrin; wherein the preliminary screening data is used to indicate the correction amount of the basic operation; The bearing vibration value and the sealing leakage rate of the stirrer are obtained to obtain an equipment state compensation coefficient; The screening data is obtained by analyzing the correction amount of the basic operation, the equipment state compensation coefficient and the historical efficiency data.

8. The intelligent control method for epoxy resin production as described in claim 6, characterized in that, The following steps are included after the strengthening operation on the operation feedback data based on the screening data to obtain strengthening data: A historical operation item whose dynamic operation efficiency index indicated by the strengthening data meets a first index requirement is selected; wherein the first index requirement is greater than or equal to index 0.85; The operation items in the emergency operation set that meet a second index requirement are replaced in priority; wherein the second index requirement is less than or equal to index 0.

6. In the case of being in the polycondensation reaction stage, a catalyst supplement rule is injected, and if the efficiency of tertiary amine catalyst decreases by more than 15%, a pre-activation instruction is added; If sodium salt catalyst residue is detected, a neutralization treatment instruction is inserted.

9. The intelligent control method for epoxy resin production as described in claim 6, characterized in that, The regulation instruction sequence data is obtained according to the heat transfer compensation factor indicated by the screening data and the dynamic operation efficiency index indicated by the strengthening data, and includes: A temperature control reference value is calculated according to the heat transfer compensation factor indicated by the screening data; A temperature correction instruction set is obtained based on the temperature control reference value; An operation priority queue is constructed according to the dynamic operation efficiency index indicated by the strengthening data, and a reconstructed operation sequence is obtained based on the operation priority queue; The regulation instruction sequence data is obtained according to the temperature correction instruction set and the reconstructed operation sequence.

10. An intelligent control device for epoxy resin production, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The processor executes the computer program to implement the method of any one of claims 1 to 9.

Images