Production control method and system for PVC (polyvinyl chloride) developing functional granules

Abstract

The invention relates to the technical field of production process control, in particular to a PVC developing functional granule production control method and system, and the method comprises the steps: calling a spectrometer to capture spectral data emitted from PVC granules in real time based on the starting of a production line, analyzing the intensity and wavelength distribution in the spectral data in real time, and generating spectral data characteristic values; and comparing and analyzing the deviation of historical data and real-time data through the spectral data characteristic value, and generating a deviation dynamic prediction analysis result. According to the invention, by monitoring and analyzing the spectral data of the PVC granules in real time, the response speed and precision of a production line are improved, and the spectral data are compared in real time, so that production deviations such as light source intensity and reaction temperature can be quickly found and adjusted, material waste is reduced, the output quality is improved, and continuous data analysis helps to adjust chemical agent feeding and heating power; product consistency is guaranteed, automatic fault diagnosis is achieved, production parameters are adjusted in time, the service life of equipment is effectively prolonged, shutdown is reduced, and cost benefits are increased.

Description

Technical Field

[0001] The invention relates to the technical field of production process control, and in particular to a production control method and system for PVC developing functional granules. Background Art

[0002] The field of production process control technology mainly involves monitoring and adjusting various parameters in the industrial production process to ensure product quality, improve efficiency and reduce waste. The technical field uses advanced sensor technology, control theory and information technology to achieve real-time data collection, analysis and feedback adjustment of the production line. In the chemical industry, production process control is particularly important because the quality of the products of many chemical reactions is highly dependent on the precise control of conditions such as temperature, pressure, chemical composition ratio and reaction time. Through the automation system, key parameters can be continuously monitored and process parameters can be adjusted according to preset targets or real-time data to ensure the stability of the production process and the consistency of the product.

[0003] Among them, the production control method of PVC developing functional granules describes a technical method specifically used to produce PVC granules with specific functionality. Functional granules have special physical or chemical properties, such as improved mechanical strength, heat resistance or specific optical properties, and are widely used in the manufacture of high-performance plastic products. The developing function refers to the granules showing or changing color under specific conditions, which is particularly important in areas such as smart packaging and safety marking. This production control method ensures that each batch of granules meets the predetermined functional standards by precisely controlling the chemical formula and processing conditions, adapting to the market demand for high quality and high consistency.

[0004] The existing production control methods of PVC developer functional granules rely on advanced sensor technology and control theory in the production process control of PVC developer functional granules, but there is a lag in data processing and feedback adjustment. Especially under high variability production conditions, such as small changes in temperature and chemical composition ratio, the existing methods cannot be accurately adjusted in real time, resulting in inconsistency between product batches. The automation in the existing technology focuses on the precise control of hardware, but ignores the potential of data-driven decision-making, which limits the optimization space of the production process and fails to effectively predict and diagnose production anomalies, resulting in larger-scale production interruptions and quality problems. The lack of flexibility and predictive adjustment mechanism makes the production line respond to emergencies in a slow manner, increasing production costs and reducing market competitiveness. Summary of the invention

[0005] The present application provides a production control method and system for PVC developer functional granules. The existing production control method for PVC developer functional granules, in the production process control of PVC developer functional granules, although relying on advanced sensor technology and control theory, has lags in data processing and feedback regulation. Especially under high variability production conditions, such as slight changes in temperature and chemical composition ratio, the existing methods cannot be accurately adjusted in real time, resulting in inconsistency between product batches. The automation in the prior art focuses on precise control of hardware, while ignoring the potential of data-driven decision-making, which limits the optimization space of the production process, fails to effectively predict and diagnose production anomalies, and leads to larger-scale production interruptions and quality problems. The lack of flexibility and predictive adjustment mechanism makes the production line respond to emergencies in a slow manner, increasing production costs and reducing market competitiveness.

[0006] In view of the above problems, the present application provides a PVC developing functional granule production control method and system.

[0007] The present application provides a PVC developing functional granule production control method, wherein the method comprises:

[0008] S1: Based on the start-up of the production line, the spectrometer is called to capture the spectral data emitted from the PVC pellets in real time, the intensity and wavelength distribution in the spectral data are analyzed in real time, and the spectral data characteristic values ​​are generated. The deviations between the historical data and the real-time data are compared and analyzed through the spectral data characteristic values, and the deviation dynamic prediction analysis results are generated;

[0009] S2: Based on the deviation dynamic prediction analysis result, adjust the light source intensity and reaction temperature in the production control, match the conditions indicated by the prediction result, generate the adjusted control parameters, perform effect test on the adjusted control parameters, measure the new spectral data and compare it with the prediction result, and generate parameter optimization effect record;

[0010] S3: Based on the parameter optimization effect record, continuous state update is performed according to temperature and pressure through continuous data analysis to generate a state estimation value, and the chemical agent delivery rate and heater power are automatically adjusted according to the state estimation value to generate a real-time control result of the production line;

[0011] S4: Utilize the real-time control results of the production line to detect abnormalities in the production process. If the prediction error exceeds a preset threshold, record the abnormality and perform a diagnosis to generate abnormality records and diagnostic results. Adjust production parameters and perform equipment maintenance based on the abnormality records and diagnostic results to generate a restored operating status result.

[0012] Preferably, the steps for obtaining the deviation dynamic prediction analysis results are specifically as follows:

[0013] S111: Based on the start-up of the production line, the spectral data is captured in real time from the spectrum emitted by the PVC pellets, and the light intensity at each wavelength is recorded, using the formula:

[0014]

[0015] Generate a real-time spectral dataset, where I ( λ represents the light intensity at wavelength λ, c i The coefficient representing the wavelength λ, a i is the wavelength index, b i is the attenuation coefficient, d i is the normalization coefficient;

[0016] S112: Extract features from the real-time spectral data set to identify key wavelengths and light intensity peaks using the formula:

[0017]

[0018] Calculate the weighted average wavelength of the spectrum and generate the spectral data characteristic value, where F represents the spectral data characteristic value, λ is the wavelength in the spectrum, and I ( λ is the light intensity at wavelength λ, p and q are weight parameters, and r is the number of roots;

[0019] S113: Compare the spectral data characteristic value with the historical data using the formula:

[0020]

[0021] Calculate the deviation of the characteristic value and generate the deviation dynamic prediction analysis result, where D represents the deviation and F represents the deviation. rcal represents the eigenvalue obtained in real time, F hist represents the historical characteristic value, and s is the index of adjustment deviation sensitivity.

[0022] Preferably, the step of obtaining the adjusted control parameters is specifically:

[0023] S211: According to the deviation dynamic prediction analysis result, the deviation degree of the light source intensity and the reaction temperature of the current production line is evaluated, using the formula:

[0024]

[0025] Calculate the weighted distance between the control parameters and the target difference to generate the control parameter deviation evaluation result, where ΔP represents the total deviation of the control parameters, P i is the current parameter value, P target is the target parameter value, w i is the weight of each parameter;

[0026] S212: According to the control parameter deviation evaluation result, a new light source intensity and reaction temperature are set, using the formula:

[0027] P new =P current ·exp ( k·ΔP )

[0028] Dynamically adjust the parameters according to the deviation size to generate new control parameter settings, where P new is the new parameter value, P currcnt is the current parameter value, ΔP is the total deviation of the control parameters, and k is the adjustment coefficient;

[0029] S213: According to the new control parameter setting and the conditions indicated by the prediction results, the optimization adjustment strategy is adopted, using the formula:

[0030]

[0031] Generate the adjusted control parameters, where C represents the adjusted control parameters, P new is the newly set parameter value, T is the threshold, and h is the adjustment sensitivity parameter.

[0032] Preferably, the steps for obtaining the parameter optimization effect record are specifically as follows:

[0033] S221: The production line is operated using the adjusted control parameters, and the output spectrum data is measured in real time using the formula:

[0034]

[0035] Strengthen the wavelength weight and attenuation effect, calculate the cumulative light intensity of the new spectrum, and generate a new spectrum data record, where S new Represents the accumulated value of the newly measured spectral data, I new( λ) is the light intensity of the wavelength under the new parameters, λ is the wavelength index in the spectrum, α and β control the influence of wavelength and attenuation coefficient, κ and ∈ are the nonlinear characteristic coefficients for adjusting the attenuation curve;

[0036] S222: Compare the new spectral data record with the pre-simulated prediction result, using the formula:

[0037]

[0038] Calculate the normalized error between the new data and the predicted data, and generate a parameter comparison record, where D represents the normalized error between the new data and the predicted data, and S new is the accumulated value of the newly measured spectral data, S prcdis the predicted spectral data accumulation value, γ is the adjustment error sensitivity index, and ρ is the bias term in the error calculation;

[0039] S223: Based on the parameter comparison record and the comparison analysis result of the new and old data, the effect of the adjusted control parameter is evaluated using the formula:

[0040]

[0041] Generate parameter optimization effect records, where R represents the parameter optimization effect record, D is the normalized error between the new data and the predicted data, δ is the amplification factor of the control error influence, and ζ and θ are the exponential attenuation factors of the adjustment error amplification.

[0042] Preferably, the step of obtaining the state estimation value is specifically as follows:

[0043] S311: Based on the parameter optimization effect record, collect the temperature and pressure data during continuous operation, using the formula:

[0044]

[0045] Generates continuous data logging results, where D t represents the data accumulation at time t, T(s) is the temperature reading, P(s) is the pressure reading, θ and φ adjust the contribution weights of temperature and pressure data, α and β are nonlinear influence coefficients, γ is the time attenuation coefficient, and δ is the coefficient for enhancing data integration;

[0046] S312: Based on the continuous data recording result, a filtering algorithm is applied to the captured continuous data to perform state estimation, using the formula:

[0047]

[0048] Generate continuous state update results, where S t is the estimated value of the state at time t, D t is the data accumulation at time t, μ and σ are used to normalize the data, η and λ are additional adjustment parameters, and ω is the sensitivity for adjusting the overall state update;

[0049] S313: Based on the continuous state update result, multiple state variables are corrected to optimize the accuracy of state prediction, using the formula:

[0050]

[0051] Generate state estimates, where E is the state estimate, S t is the state estimate at time t, ξ, δ, and θ adjust the responsiveness and smoothness of the state estimate.

[0052] Preferably, the steps for obtaining the real-time control result of the production line are specifically as follows:

[0053] S321: Based on the state estimation value, evaluate and analyze the current operating state of the production equipment, using the formula:

[0054]

[0055] Generate state analysis results, where R represents the state stability index, max, min, mean, and std represent the maximum, minimum, mean, and standard deviation of the state estimate, ∈ is a small quantity, ω is the weight coefficient of the standard deviation, and E s is the sequence of state estimates;

[0056] S322: According to the state analysis result, the rate of chemical release is adjusted using the formula:

[0057]

[0058] Calculate the new chemical agent delivery rate and generate the chemical agent delivery adjustment result, where V c is the adjusted chemical agent delivery rate, V0 is the baseline delivery rate, k is the adjustment coefficient, τ is the target stability index, ρ is the adjustment parameter, σ is the adaptability coefficient, and R is the state stability index;

[0059] S323: According to the estimated state value, adjust the power setting of the heater to match the real-time production demand, using the formula:

[0060] P h =P0·e λ·(R-τ) / (μ+ν·R)

[0061] Generates heater power adjustment result, where P h is the adjusted heater power, P0 is the reference power, λ is the adjustment sensitivity parameter, τ is the target stability index, μ is the scaling factor, ν is the dynamic adjustment factor, and R is the state stability index;

[0062] S324: Based on the chemical agent introduction rate and the heater power adjustment result, the introduction rate and power are monitored and adjusted in real time to generate a real-time control result of the production line.

[0063] Preferably, the step of obtaining the operating status result after recovery is specifically:

[0064] S411: Using the real-time control results of the production line, monitor the indicators in the production process using the formula:

[0065]

[0066] Calculate the prediction error. If it exceeds the preset threshold, mark it as an anomaly and generate an anomaly detection result, where AX is the prediction error and V act Represents the real-time measurement value, V cxp represents the expected value, β and γ are adjustment coefficients, and δ is the bias term;

[0067] S412: Based on the abnormal detection result, the abnormal data is automatically recorded and a preliminary diagnosis plan is initiated, using the formula:

[0068]

[0069] Calculate the weighted cubic error, analyze the fluctuation and stability of the parameters, and generate abnormal records and diagnostic results, where BY represents the weighted cubic error of the parameter fluctuation, x i Indicates the parameter value when an exception occurs. is the average value of the parameter, α i is the weight of the parameter;

[0070] S413: According to the abnormal records and diagnosis results, the associated production parameters are adjusted and equipment maintenance is performed, and the adjusted parameter efficiency is calculated using the formula:

[0071]

[0072] Generate the restored operating status results, where CZ is the adjusted efficiency, P new and P old represent the production parameters before and after adjustment respectively, k is the efficiency adjustment coefficient, and ξ is the stabilization term.

[0073] A PVC developing functional granule production control system, the system comprising:

[0074] The spectrum capture module starts based on the production line, adjusts the position and sensitivity of the spectrometer and captures the spectrum data emitted from the PVC pellets, records the light intensity and wavelength distribution data, and obtains the spectrum characteristic value;

[0075] The data analysis and control module uses the spectral characteristic values ​​to perform quantitative processing on the spectral data, calculates the light intensity distribution and wavelength changes, compares the real-time data with the historical data, adjusts the light source intensity and reaction temperature, verifies the spectral data, and establishes the adjusted control parameters;

[0076] The parameter optimization feedback module captures spectral data through the adjusted control parameters, compares the changes in spectral data before and after the adjustment, analyzes the adjustment effect, and constructs a parameter optimization effect record;

[0077] The status update and adjustment module calculates the chemical agent delivery rate and heater power adjustment value based on the parameter optimization effect record, adjusts the equipment settings in real time, automatically updates the production status, and generates real-time production line control results;

[0078] The abnormal monitoring and maintenance module monitors the real-time control results of the production line, identifies deviations and abnormalities, records and diagnoses abnormal conditions, adjusts production parameters and equipment maintenance strategies, and obtains the operating status results after recovery.

[0079] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0080] By real-time monitoring and analysis of the spectral data of PVC pellets, the response speed and accuracy of the production line can be effectively improved. Real-time capture of spectral data and comparison with historical data allows immediate discovery of production deviations, thereby quickly adjusting the light source intensity and reaction temperature. This instant feedback mechanism not only reduces material waste in production, but also improves the efficiency and output quality of the entire production process. Through continuously updated data analysis, real-time adjustment of chemical agent delivery rate and heater power further ensures product consistency and functional standards. By automatically diagnosing abnormalities in the production process and adjusting production parameters, the timeliness of equipment maintenance is ensured, thereby extending equipment life and reducing downtime caused by equipment failure, improving production efficiency, ensuring product quality, and bringing cost benefits to the company.

[0081] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0082] Figure 1 The present invention proposes an overall flow chart of a production control method for PVC developing functional granules;

[0083] Figure 2 A flowchart of the deviation dynamic prediction analysis results of a PVC developer functional granule production control method proposed by the present invention;

[0084] Figure 3 A flow chart of adjusted control parameters of a production control method for PVC developing functional granules is provided for the present invention;

[0085] Figure 4 A flow chart for recording the parameter optimization effect of a PVC developing functional granule production control method proposed by the present invention;

[0086] Figure 5A flow chart of state estimation value of a PVC developing functional granule production control method is proposed for the present invention;

[0087] Figure 6 A flowchart of the real-time control results of the production line of a PVC developer functional granule production control method proposed by the present invention;

[0088] Figure 7 The present invention proposes a flow chart of the operating status results after recovery of a PVC developing functional granule production control method. DETAILED DESCRIPTION

[0089] The present application provides a production control method and system for PVC developing functional granules.

[0090] Application Overview

[0091] The production control method of PVC developer functional granules in the existing technology In the production process control of PVC developer functional granules, although it relies on advanced sensor technology and control theory, there is a lag in data processing and feedback adjustment. Especially under high variability production conditions, such as slight changes in temperature and chemical composition ratio, the existing methods cannot be accurately adjusted in real time, resulting in inconsistency between product batches. The automation in the existing technology focuses on the precise control of hardware and ignores the potential of data-driven decision-making, which limits the optimization space of the production process and fails to effectively predict and diagnose production anomalies, resulting in larger-scale production interruptions and quality problems. The lack of flexibility and predictive adjustment mechanism makes the production line respond to emergencies in a slow manner, increasing production costs and reducing market competitiveness.

[0092] In response to the above technical problems, the overall idea of ​​the technical solution provided by this application is as follows:

[0093] Example

[0094] like Figure 1 As shown, the present application provides a PVC developing functional granule production control method, wherein the method comprises:

[0095] S1: Based on the start-up of the production line, the spectrometer is called to capture the spectral data emitted from the PVC pellets in real time, the intensity and wavelength distribution in the spectral data are analyzed in real time, and the spectral data characteristic values ​​are generated. The deviations between the historical data and the real-time data are compared and analyzed through the spectral data characteristic values, and the deviation dynamic prediction analysis results are generated;

[0096] S2: Based on the results of the dynamic prediction analysis of the deviation, adjust the light source intensity and reaction temperature in the production control, match the conditions indicated by the prediction results, generate the adjusted control parameters, test the effects of the adjusted control parameters, measure the new spectral data and compare it with the prediction results, and generate parameter optimization effect records;

[0097] S3: Based on the parameter optimization effect record, through continuous data analysis, continuous state update is performed according to temperature and pressure to generate state estimation values. According to the state estimation values, the chemical agent delivery rate and heater power are automatically adjusted to generate real-time production line control results;

[0098] S4: Use the real-time control results of the production line to detect anomalies in the production process. If the prediction error exceeds the preset threshold, record the anomaly and diagnose it, generate anomaly records and diagnostic results, adjust production parameters and perform equipment maintenance based on the anomaly records and diagnostic results, and generate the operating status results after recovery.

[0099] The results of dynamic prediction analysis of deviations include wavelength deviation value, light intensity deviation value, and time deviation performance. The adjusted control parameters include light source intensity level, set reaction temperature, and environmental matching degree. The parameter optimization effect records include comparison values ​​before and after optimization, adjustment reaction effect, and stability index. The real-time regulation results of the production line include adjusted chemical dosage, adjusted power level, and updated control frequency. The abnormal records and diagnostic results include recorded abnormal events, diagnosed error codes, and preventive measures taken. The operating status results after recovery include adjusted parameter stability, equipment maintenance integrity, and recovery efficiency evaluation.

[0100] Specifically, if Figure 2 As shown in FIG. 1 , the steps for obtaining the deviation dynamic prediction analysis results are as follows:

[0101] S111: Based on the start-up of the production line, the spectral data is captured in real time from the spectrum emitted by the PVC pellets, and the light intensity at each wavelength is recorded, using the formula:

[0102]

[0103] Generate a real-time spectral dataset, where I ( λ ) represents the light intensity at wavelength λ, c i The coefficient representing the wavelength λ, a i is the wavelength index, b i is the attenuation coefficient, d i is the normalization coefficient;

[0104] S112: Extract features from the real-time spectral data set to identify key wavelengths and light intensity peaks using the formula:

[0105]

[0106] Calculate the weighted average wavelength of the spectrum to generate the spectral data characteristic value, where F represents the spectral data characteristic value, λ is the wavelength in the spectrum, I(λ) is the light intensity at wavelength λ, p and q are weight parameters, and r is the number of roots;

[0107] S113: Use the spectral data characteristic value to compare with the historical data, using the formula:

[0108]

[0109] Calculate the deviation of the characteristic value and generate the deviation dynamic prediction analysis result, where D represents the deviation and F represents the deviation. rcal represents the eigenvalue obtained in real time, F hist represents the historical characteristic value, and s is the index of adjustment deviation sensitivity.

[0110] The formula for light intensity at wavelength λ is:

[0111]

[0112] Parameter Description:

[0113] I(λ ) : light intensity at wavelength λ;

[0114] c i : spectral intensity coefficient;

[0115] a i : wavelength index, the effect of adjusting wavelength;

[0116] b i : Attenuation coefficient, controls the attenuation rate of wavelength;

[0117] d i : Normalization coefficient, ensuring data standardization;

[0118] λ: wavelength of the spectrum;

[0119] Assume n = 2, that is, there are two wavelength data points, set the following parameters: c1 = 1.2, c2 = 0.8, a1 = 2, a2 ​​= 1, b1 = 0.05, b2 = 0.1, d1 = d2 = 1, λ1 = 500nm, λ2 = 600nm

[0120] Calculation example:

[0121] I(500)=1.2·500 2 ·e -0.05·500 1+0.8·600·e -0.1·600 1

[0122] I(500)≈1.2·250000·e -25 +0.8·600·e -60

[0123] I(500)≈1.2·250000·1.39×10 -11+0.8 600 8.756 × 10 -27

[0124] I(500)≈4.158×10 -6 =0.000004158

[0125] This calculation example shows the light intensity at a wavelength of 500 nm, where e -25 and e -60 This is the result of exponential decay.

[0126] Spectral data characteristic value formula:

[0127]

[0128] F: characteristic value of the spectrum;

[0129] λ: wavelength in the spectrum;

[0130] I ( λ): light intensity corresponding to wavelength;

[0131] p and q are weight parameters, and r is the number of roots;

[0132] Assumptions: p = 2, q = 2, r = 2;

[0133] Use the I from the previous step ( λ) value, calculation example:

[0134]

[0135] F≈20.76

[0136] This calculation example shows the weighted eigenvalues ​​of spectral data

[0137] The relative deviation formula of the eigenvalue is:

[0138]

[0139] D: relative deviation;

[0140] F rcal : Real-time characteristic value;

[0141] F hist : historical characteristic value;

[0142] s: index of adjustment bias sensitivity;

[0143] Assumption: F real =20.76, F hist =20, s=1;

[0144] Calculation example:

[0145]

[0146]

[0147] D=0.038

[0148] This calculation example shows the results of a deviation analysis compared to historical data.

[0149] Specifically, if Figure 3 As shown, the steps for obtaining the adjusted control parameters are as follows:

[0150] S211: Based on the deviation dynamic prediction analysis results, evaluate the deviation degree of the light source intensity and reaction temperature of the current production line, using the formula:

[0151]

[0152] Calculate the weighted distance between the control parameters and the target difference to generate the control parameter deviation evaluation result, where ΔP represents the total deviation of the control parameters, P i is the current parameter value, P target is the target parameter value, w i is the weight of each parameter;

[0153] S212: According to the control parameter deviation evaluation result, set the new light source intensity and reaction temperature, using the formula:

[0154] P ncw =P current ·exp ( k·ΔP )

[0155] Dynamically adjust the parameters according to the deviation size to generate new control parameter settings, where P new is the new parameter value, P currcnt is the current parameter value, ΔP is the total deviation of the control parameters, and k is the adjustment coefficient;

[0156] S213: According to the new control parameter settings and the conditions indicated by the prediction results, the optimization adjustment strategy is adopted, using the formula:

[0157]

[0158] Generate the adjusted control parameters, where C represents the adjusted control parameters, P new is the newly set parameter value, T is the threshold, and h is the adjustment sensitivity parameter.

[0159] The formula for the sum of deviations of the control parameters is derived as follows:

[0160]

[0161] Assumption: Parameter n = 2 (consider two control parameters: light source intensity and reaction temperature);

[0162] P1 current light intensity = 500lux, P target1 Target light intensity = 450lux;

[0163] P2 current reaction temperature = 300°C, P target2 Target reaction temperature = 290°C;

[0164] Weights w1=0.5, w2=0.5;

[0165] Calculate the light source intensity deviation:

[0166]

[0167] Calculate the reaction temperature deviation:

[0168]

[0169] Calculate the total deviation:

[0170]

[0171] This deviation value ΔP=0.0822 represents the relative distance from the current parameter to the target parameter, and is used to quantify the adjustment requirements of the control parameters.

[0172] The formula for the newly set parameter value is derived as follows:

[0173] P new =P current ·exp ( k·ΔP )

[0174] Assumptions: adjustment factor k = 0.1, use ΔP = 0.0822;

[0175] Adjust the light intensity:

[0176] P new1 =500·exp(0.1·0.0822)≈500·1.0086≈504.3lux,

[0177] Adjust the reaction temperature:

[0178] P new2 =300·exp(0.1·0.0822)≈300·1.0086≈302.58℃,

[0179] The new control parameter values, 504.3Iux and 302.58°C, represent the fine-tuning required relative to the current state to achieve the target state.

[0180] The formula derivation of the adjusted control parameters:

[0181]

[0182] Assumption: preset safety threshold T = 500 lux and 300 °C, adjust sensitivity parameter h = 10;

[0183] Light source intensity control parameters:

[0184]

[0185] Reaction temperature control parameters:

[0186]

[0187] The values ​​(0.605 and 0.564) represent the response strength of the adjusted control parameters relative to the set threshold, which reflects the adaptability of the new parameter settings.

[0188] Specifically, if Figure 4 As shown in the figure, the specific steps for obtaining parameter optimization effect records are as follows:

[0189] S221: Run the production line with the adjusted control parameters and measure the output spectral data in real time using the formula:

[0190]

[0191] Strengthen the wavelength weight and attenuation effect, calculate the cumulative light intensity of the new spectrum, and generate a new spectrum data record, where S new Represents the accumulated value of the newly measured spectral data, I new (λ) is the light intensity at the wavelength under the new parameters, λ is the wavelength index in the spectrum, α and β control the influence of wavelength and attenuation coefficient, κ and ∈ are the nonlinear characteristic coefficients for adjusting the attenuation curve;

[0192] S222: Compare the new spectral data record with the predicted results of the previous simulation using the formula:

[0193]

[0194] Calculate the normalized error between the new data and the predicted data, and generate a parameter comparison record, where D represents the normalized error between the new data and the predicted data, and S new is the accumulated value of the newly measured spectral data, S prcd is the predicted spectral data accumulation value, γ is the adjustment error sensitivity index, and ρ is the bias term in the error calculation;

[0195] S223: Based on the parameter comparison records and the comparative analysis results of the new and old data, the effect of the adjusted control parameters is evaluated using the formula:

[0196]

[0197] Generate parameter optimization effect records, where R represents the parameter optimization effect record, D is the normalized error between the new data and the predicted data, δ is the amplification factor of the control error influence, and ζ and θ are the exponential attenuation factors of the adjustment error amplification.

[0198] The cumulative value formula of the newly measured spectral data is:

[0199]

[0200] I new (λ): The light intensity at wavelength λ measured under the new control parameters. For example, the light intensity measured by the spectrometer at wavelength λ = 500nm is 20 units;

[0201] λ: wavelength, usually in nanometers (nm). In practical applications, λ may range from 400nm to 700nm.

[0202] α and β: These are exponential coefficients used to adjust the wavelength effect and attenuation, for example, set α = 2 and β = 0.01;

[0203] κ and ∈: coefficients used to adjust nonlinear characteristics, for example, set κ=0.5 and ∈=3.

[0204] Set the wavelength λ = 500nm, light intensity I new (500) = 20;

[0205] Using the above parameters, calculate each term in the formula:

[0206] S new (500) = 20 500 2 ·e -0.01·500 +0.5 500 3 =5000000·0.9933+62500000=6226600

[0207] This calculated value S new (500) represents the spectral cumulative response after adjusting the parameters at a wavelength of 500 nm.

[0208] The formula for the normalized error between new data and predicted data is:

[0209]

[0210] Snew : Accumulated value of newly measured spectral data;

[0211] S pred : Predicted spectral data, such as predicted S pred (500) = 6200000;

[0212] γ and ρ: exponent and bias term for adjusting error sensitivity, set γ = 1 and ρ = 100;

[0213] Calculate the error based on the actual measured and predicted data:

[0214]

[0215] The error D(500) shows how much the new data differ from the predicted data at 500 nm.

[0216] Parameter optimization effect recording formula:

[0217]

[0218] D: normalized error between new data and predicted data;

[0219] δ is the amplification factor of the control error, ζ and θ are the exponential attenuation factors of the adjustment error amplification, and δ=1, ζ=1, θ=1;

[0220] Use the error D and adjustment factor to calculate the optimization effect record:

[0221]

[0222] This result R represents the effect of optimization at 500nm, indicating a slight improvement in the effect.

[0223] Specifically, if Figure 5 As shown in Figure 1, the steps for obtaining the state estimation value are as follows:

[0224] S311: Based on the parameter optimization effect record, collect the temperature and pressure data during continuous operation, using the formula:

[0225]

[0226] Generates continuous data logging results, where D t represents the data accumulation at time t, T(s) is the temperature reading, P(s) is the pressure reading, θ and φ adjust the contribution weights of temperature and pressure data, α and β are nonlinear influence coefficients, γ is the time attenuation coefficient, and δ is the coefficient for enhancing data integration;

[0227] S312: Based on the continuous data recording results, a filtering algorithm is applied to the captured continuous data to perform state estimation, using the formula:

[0228]

[0229] Generate continuous state update results, where S t is the estimated value of the state at time t, D t is the data accumulation at time t, μ and σ are used to normalize the data, η and λ are additional adjustment parameters, and ω is the sensitivity for adjusting the overall state update;

[0230] S313: Based on the continuous state update results, multiple state variables are corrected to optimize the accuracy of state prediction, using the formula:

[0231]

[0232] Generate state estimates, where E is the state estimate, S t is the state estimate at time t, ξ, δ, and θ adjust the responsiveness and smoothness of the state estimate.

[0233] The formula for data accumulation at time t is:

[0234]

[0235] T(s) and P(s): real-time measured temperature and pressure data;

[0236] θ and φ: weight coefficients, which determine the influence of temperature and pressure data in the overall function;

[0237] α and β: nonlinear influence coefficients, adjusting the sensitivity of temperature and pressure readings;

[0238] γ: time decay coefficient, used to reduce the influence of early measurements;

[0239] δ: Overall magnification factor, used to adjust the scale of the data.

[0240] Assume that within time t, the temperature T(s) and pressure P(s) remain constant, for example, T(s) = 300K and P(s) = 100 kPa, set θ = 0.5, φ = 1.0, α = 2, β = 1, γ = 0.1, δ = 1;

[0241] Calculate D t :

[0242]

[0243]

[0244]

[0245]

[0246] If t = 10 seconds, the result is:

[0247] This value represents the accumulated weighted temperature and pressure adjustments from t=0 to t=10 seconds.

[0248] The formula for the state estimate at time t is:

[0249]

[0250] D t : Data accumulation at time t;

[0251] μ and σ: mean and standard deviation of normalized data;

[0252] η and λ: parameters for adjusting data smoothness;

[0253] ω: state update sensitivity adjustment parameter;

[0254] Assumption: μ=4000000, σ=500000, η=0.05, λ=0.00001, ω=2;

[0255] Calculate S t :

[0256]

[0257]

[0258] S t =0.3585+0.1·0.9999

[0259] S t =0.3585+0.09999≈0.4585

[0260] This condition estimate represents a comprehensive assessment of the equipment's condition over a given period of time.

[0261] State estimation formula:

[0262]

[0263] S t : The estimated value of the state at time t;

[0264] ξ, δ, and θ: parameters that adjust responsiveness and smoothness;

[0265] Assumption: ξ=0.5, δ=1, θ=1;

[0266] Calculate E:

[0267] E=(0.45850.5 (1-0.4585) 0.5 ) 1×1 E=(0.677·0.732) 1 E=0.495

[0268] This value represents the final device state estimate and reflects the comprehensive performance of the device under current conditions.

[0269] Specifically, if Figure 6 As shown in the figure, the steps for obtaining the real-time control results of the production line are as follows:

[0270] S321: Based on the estimated state value, evaluate and analyze the current operating state of the production equipment using the formula:

[0271]

[0272] Generate state analysis results, where R represents the state stability index, max, min, mean, and std represent the maximum, minimum, mean, and standard deviation of the state estimate, ∈ is a small quantity, ω is the weight coefficient of the standard deviation, and E s is the sequence of state estimates;

[0273] S322: According to the status analysis results, adjust the rate of chemical release using the formula:

[0274]

[0275] Calculate the new chemical agent delivery rate and generate the chemical agent delivery adjustment result, where V c is the adjusted chemical agent delivery rate, V0 is the baseline delivery rate, k is the adjustment coefficient, τ is the target stability index, ρ is the adjustment parameter, σ is the adaptability coefficient, and R is the state stability index;

[0276] S323: According to the estimated state value, the power setting of the heater is adjusted to match the real-time production demand, using the formula:

[0277] P h =P0·e λ·(R-τ) / (μ+ν·R)

[0278] Generates heater power adjustment result, where P h is the adjusted heater power, P0 is the reference power, λ is the adjustment sensitivity parameter, τ is the target stability index, μ is the scaling factor, ν is the dynamic adjustment factor, and R is the state stability index;

[0279] S324: Based on the chemical agent delivery rate and the heater power adjustment results, the delivery rate and power are monitored and adjusted in real time to generate real-time control results for the production line.

[0280] State stability index formula:

[0281]

[0282] E s : A sequence of state estimates, such as the estimated value every minute in the past hour;

[0283] max(E s )、min(E s )、mean(E s )、std(E s ): Calculate E s The maximum, minimum, mean and standard deviation of

[0284] ∈: small amount to prevent the denominator from being zero, usually set to 0.01;

[0285] ω: weight coefficient of standard deviation, set to 0.5;

[0286] Assumption E s =[0.95, 0.90, 0.92, 0.88, 0.91], max(E s )=0.95,min(E s )=0.88,mean(E s )=0.912,std(E s )=0.025;

[0287] Substitute into the formula to calculate:

[0288]

[0289] This R value represents the ratio of the volatility of the state estimate to its overall level. A smaller value indicates that the equipment state is relatively stable.

[0290] Adjusted chemical release rate formula:

[0291]

[0292] V0: Base delivery rate, for example 100 units / hour;

[0293] k: adjustment coefficient, set to 0.2;

[0294] τ: target stability index, set to 0.05;

[0295] ρ: adjustment parameter, set to 0.01;

[0296] σ: flexibility adjustment coefficient, set to 0.1;

[0297] Calculate V c :

[0298]

[0299]

[0300] This V c The value represents the new chemical delivery rate, 107.56 units / hour, which has increased relative to the baseline value in response to the needs of the equipment.

[0301] Adjusted heater power formula:

[0302] P h =P0·e λ·(R-τ) / (μ+ν·R)

[0303] P0: base power, for example 500 watts;

[0304] λ: Adjustment sensitivity parameter, set to 3;

[0305] τ: target stability index, same as above;

[0306] μ: scaling factor, set to 0.1;

[0307] V: Dynamic adjustment factor, set to 0.05.

[0308] Calculate P h :

[0309] P h =500·e 3·(0.075-0.05) / (0.1+0.05·0.075)

[0310] P h =500·e 3·0.025 / 0.103625 =500·e 0.7237 ≈515

[0311] This P h The value represents the adjusted heater power, 515 watts, reflecting the need to increase the power to accommodate the current production line status.

[0312] Specifically, if Figure 7 As shown, the steps for obtaining the running status result after recovery are as follows:

[0313] S411: Using the real-time control results of the production line, monitor the indicators in the production process using the formula:

[0314]

[0315] Calculate the prediction error. If it exceeds the preset threshold, mark it as an anomaly and generate an anomaly detection result, where AX is the prediction error and V act Represents the real-time measurement value, V cxprepresents the expected value, β and γ are adjustment coefficients, and δ is the bias term;

[0316] S412: Based on the abnormal detection results, the abnormal data is automatically recorded and the preliminary diagnosis plan is initiated, using the formula:

[0317]

[0318] Calculate the weighted cubic error, analyze the fluctuation and stability of the parameters, and generate abnormal records and diagnostic results, where BY represents the weighted cubic error of the parameter fluctuation, x i Indicates the parameter value when an exception occurs. is the average value of the parameter, α i is the weight of the parameter;

[0319] S413: According to the abnormal records and diagnosis results, adjust the related production parameters and perform equipment maintenance, and calculate the adjusted parameter efficiency using the formula:

[0320]

[0321] Generate the restored operating status results, where CZ is the adjusted efficiency, P new and P old represent the production parameters before and after adjustment respectively, k is the efficiency adjustment coefficient, and ξ is the stabilization term.

[0322] Anomaly detection result formula:

[0323]

[0324] V act : Real-time measurement value, assumed to be 100 units;

[0325] V exp : expected value, assumed to be 90 units;

[0326] β and γ: adjustment coefficients, taking into account data volatility and bias adjustment, assumed to be 1.1 and 1.0 respectively;

[0327] δ: bias term, used to adjust the sensitivity of error judgment, assumed to be 5 units;

[0328] Compute the squares of the adjusted actual and expected values:

[0329]

[0330]

[0331] Compute the difference and take the square root to get the error:

[0332]

[0333] The calculated error value AX=58.85 represents the adjusted deviation between the current actual value and the expected value, and is marked as abnormal if it exceeds the threshold.

[0334] Abnormal records and diagnostic results formula:

[0335]

[0336] x i : Parameter values ​​when abnormal, assuming there are three parameter values ​​100, 110, and 95;

[0337] average value,

[0338] α i : Weight coefficient, assumed to be 1;

[0339] Compute the cube of the difference between each parameter and the mean:

[0340] |100-101.67 | 3 =2.74 3 =20.5

[0341] 110-101.67 | 3 =8.33 3 =578.9

[0342] 95-101.67 | 3 =6.67 3 =296.3

[0343] Compute the weighted cubic difference:

[0344] The calculated BY = 298.57 represents the weighted cubic deviation of the abnormal parameter values, and higher values ​​reflect obvious volatility or stability problems.

[0345] Adjusted efficiency formula:

[0346]

[0347] P new and P old : Represent the production parameters before and after adjustment, assuming that the production parameters before adjustment are 90 units and the production parameters after adjustment are 95 units;

[0348] k: efficiency adjustment factor, assumed to be 1.2;

[0349] ξ: stabilization term to smooth the adjustment process, assumed to be 10 units;

[0350] Compute the adjusted values ​​of the squared parameters after adjustment and the squared old parameters:

[0351]

[0352]

[0353] Calculate the efficiency adjustment:

[0354]

[0355] The calculated CZ=120.36 represents the adjusted parameter efficiency, and the value is used to determine whether the adjusted production status has returned to normal.

[0356] A PVC developing functional granule production control system, the system comprises:

[0357] The spectrum capture module starts based on the production line, adjusts the position and sensitivity of the spectrometer and captures the spectrum data emitted from the PVC pellets, records the light intensity and wavelength distribution data, and obtains the spectrum characteristic value;

[0358] The data analysis and control module uses spectral characteristic values ​​to perform quantitative processing on spectral data, calculates light intensity distribution and wavelength changes, compares real-time data with historical data, adjusts light source intensity and reaction temperature, verifies spectral data, and establishes adjusted control parameters;

[0359] The parameter optimization feedback module captures spectral data by adjusting the control parameters, compares the changes in spectral data before and after the adjustment, analyzes the adjustment effect, and builds a record of parameter optimization effects;

[0360] The status update and adjustment module calculates the chemical agent delivery rate and heater power adjustment value based on the parameter optimization effect record, adjusts the equipment settings in real time, automatically updates the production status, and generates real-time production line control results;

[0361] The abnormal monitoring and maintenance module monitors the real-time control results of the production line, identifies deviations and abnormalities, records and diagnoses abnormal conditions, adjusts production parameters and equipment maintenance strategies, and obtains the operating status results after recovery.

[0362] Although the present application has been described in conjunction with specific features and embodiments thereof, it is obvious that various modifications and combinations may be made thereto without departing from the spirit and scope of the present application. Accordingly, this specification and the drawings are merely exemplary illustrations of the present application as defined by the appended claims, and are deemed to have covered any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is intended to include these modifications and variations.

Claims

1. A PVC developing functional granule production control method, characterized in that: The method comprises: Based on the start-up of the production line, the spectrometer is called to capture the spectral data emitted from the PVC pellets in real time, the intensity and wavelength distribution in the spectral data are analyzed in real time, and the spectral data characteristic values ​​are generated. The deviations between the historical data and the real-time data are compared and analyzed through the spectral data characteristic values, and the deviation dynamic prediction analysis results are generated; Based on the deviation dynamic prediction analysis results, adjust the light source intensity and reaction temperature in production control, match the conditions indicated by the prediction results, generate adjusted control parameters, perform effect tests on the adjusted control parameters, measure new spectral data and compare them with the prediction results, and generate parameter optimization effect records; Based on the parameter optimization effect record, continuous state updates are performed according to temperature and pressure through continuous data analysis to generate state estimation values. According to the state estimation values, the chemical agent delivery rate and heater power are automatically adjusted to generate real-time production line control results; The real-time control results of the production line are used to detect anomalies in the production process. If the prediction error exceeds a preset threshold, the anomaly is recorded and diagnosed to generate anomaly records and diagnostic results. Production parameters are adjusted and equipment maintenance is performed based on the anomaly records and diagnostic results to generate operating status results after recovery.

2. The PVC developing functional granule production control method according to claim 1, characterized in that: The steps for obtaining the deviation dynamic prediction analysis results are specifically as follows: Based on the production line startup, the spectral data is captured in real time from the spectrum emitted by the PVC pellets, and the light intensity at each wavelength is recorded, using the formula: Generate a real-time spectral dataset, where I ( λ ) represents the light intensity at wavelength λ, c i The coefficient representing the wavelength λ, a i is the wavelength index, b i is the attenuation coefficient, d i is the normalization coefficient; Feature extraction is performed on the real-time spectral data set to identify key wavelengths and light intensity peaks using the formula: Calculate the weighted average wavelength of the spectrum and generate the spectral data characteristic value, where F represents the spectral data characteristic value, λ is the wavelength in the spectrum, and I ( λ ) is the light intensity at wavelength λ, p and q are weight parameters, and r is the number of roots; The characteristic values ​​of the spectral data are compared with the historical data using the formula: Calculate the deviation of the characteristic value and generate the deviation dynamic prediction analysis result, where D represents the deviation and F represents the deviation. rcal represents the eigenvalue obtained in real time, F hist represents the historical characteristic value, and s is the index of adjustment deviation sensitivity.

3. The PVC developing functional granule production control method according to claim 2, characterized in that: The steps for obtaining the adjusted control parameters are specifically as follows: According to the deviation dynamic prediction analysis results, the deviation degree of the light source intensity and reaction temperature of the current production line is evaluated using the formula: Calculate the weighted distance between the control parameters and the target difference to generate the control parameter deviation evaluation result, where ΔP represents the total deviation of the control parameters, P i is the current parameter value, P target is the target parameter value, w i is the weight of each parameter; According to the control parameter deviation evaluation results, the new light source intensity and reaction temperature are set using the formula: P new =P current ·exp ( k·ΔP ) Dynamically adjust the parameters according to the deviation size to generate new control parameter settings, where P new is the new parameter value, P currcnt is the current parameter value, ΔP is the total deviation of the control parameters, and k is the adjustment coefficient; According to the new control parameter settings and the conditions indicated by the prediction results, the optimization adjustment strategy is adopted, using the formula: Generate the adjusted control parameters, where C represents the adjusted control parameters, P new is the newly set parameter value, T is the threshold, and h is the adjustment sensitivity parameter.

4. The PVC developing functional granule production control method according to claim 3, characterized in that: The steps for obtaining the parameter optimization effect record are specifically as follows: The production line is operated using the adjusted control parameters, and the output spectral data is measured in real time using the formula: Strengthen the wavelength weight and attenuation effect, calculate the cumulative light intensity of the new spectrum, and generate a new spectrum data record, where S new Represents the accumulated value of the newly measured spectral data, I new (λ) is the light intensity at the wavelength under the new parameters, λ is the wavelength index in the spectrum, α and β control the influence of wavelength and attenuation coefficient, κ and ∈ are the nonlinear characteristic coefficients for adjusting the attenuation curve; The new spectral data record is compared with the predicted results of the previous simulation using the formula: Calculate the normalized error between the new data and the predicted data, and generate a parameter comparison record, where D represents the normalized error between the new data and the predicted data, and S new is the accumulated value of the newly measured spectral data, S prcd is the predicted spectral data accumulation value, γ is the adjustment error sensitivity index, and ρ is the bias term in the error calculation; Based on the parameter comparison records and the comparative analysis results of the new and old data, the effect of the adjusted control parameters is evaluated using the formula: Generate parameter optimization effect records, where R represents the parameter optimization effect record, D is the normalized error between the new data and the predicted data, δ is the amplification factor of the control error influence, and ζ and θ are the exponential attenuation factors of the adjustment error amplification.

5. The PVC developing functional granule production control method according to claim 4, characterized in that: The steps for obtaining the state estimation value are specifically as follows: Based on the parameter optimization effect record, the temperature and pressure data during continuous operation are collected and the formula is used: Generates continuous data logging results, where D t represents the data accumulation at time t, T(s) is the temperature reading, P(s) is the pressure reading, θ and φ adjust the contribution weights of temperature and pressure data, α and β are nonlinear influence coefficients, γ is the time attenuation coefficient, and δ is the coefficient for enhancing data integration; Based on the continuous data recording results, a filtering algorithm is applied to the captured continuous data to perform state estimation, using the formula: Generate continuous state update results, where S t is the estimated value of the state at time t, D t is the data accumulation at time t, μ and σ are used to normalize the data, η and λ are additional adjustment parameters, and ω is the sensitivity for adjusting the overall state update; Based on the continuous state update results, multiple state variables are corrected to optimize the accuracy of state prediction, using the formula: Generate state estimates, where E is the state estimate, S t is the state estimate at time t, ξ, δ, and θ adjust the responsiveness and smoothness of the state estimate.

6. The PVC developing functional granule production control method according to claim 5, characterized in that: The steps for obtaining the real-time control result of the production line are specifically as follows: Based on the estimated state value, the current operating state of the production equipment is evaluated and analyzed using the formula: Generate state analysis results, where R represents the state stability index, max, min, mean, and std represent the maximum, minimum, mean, and standard deviation of the state estimate, ∈ is a small quantity, ω is the weight coefficient of the standard deviation, and E s is the sequence of state estimates; According to the state analysis results, the rate of chemical release is adjusted using the formula: Calculate the new chemical agent delivery rate and generate the chemical agent delivery adjustment result, where V c is the adjusted chemical agent delivery rate, V0 is the baseline delivery rate, k is the adjustment coefficient, τ is the target stability index, ρ is the adjustment parameter, σ is the adaptability coefficient, and R is the state stability index; Based on the state estimate, the heater power setting is adjusted to match the real-time production demand using the formula: Q h =P0·e λ·(R-τ) / (μ+ν·R) Generates heater power adjustment result, where P h is the adjusted heater power, P0 is the reference power, λ is the adjustment sensitivity parameter, τ is the target stability index, μ is the scaling factor, ν is the dynamic adjustment factor, and R is the state stability index; Combined with the chemical agent delivery rate and heater power adjustment results, the delivery rate and power are monitored and adjusted in real time to generate real-time control results of the production line.

7. The PVC developing functional granule production control method according to claim 6, characterized in that: The steps for obtaining the operating status result after recovery are specifically as follows: The real-time control results of the production line are used to monitor the indicators in the production process, using the formula: Calculate the prediction error. If it exceeds the preset threshold, mark it as an anomaly and generate an anomaly detection result, where AX is the prediction error and V act Represents the real-time measurement value, V cxp represents the expected value, β and γ are adjustment coefficients, and δ is the bias term; Based on the abnormal detection results, the abnormal data is automatically recorded and a preliminary diagnosis plan is initiated, using the formula: Calculate the weighted cubic error, analyze the fluctuation and stability of the parameters, and generate abnormal records and diagnostic results, where BY represents the weighted cubic error of the parameter fluctuation, x i Indicates the parameter value when an exception occurs. is the average value of the parameter, α i is the weight of the parameter; According to the abnormal records and diagnosis results, the associated production parameters are adjusted and equipment maintenance is performed, and the efficiency of the adjusted parameters is calculated using the formula: Generate the restored operating status results, where CZ is the adjusted efficiency, P new and P old represent the production parameters before and after adjustment respectively, k is the efficiency adjustment coefficient, and ξ is the stabilization term.

8. A PVC developing functional granule production control system, characterized in that: According to a PVC developing functional granule production control method according to any one of claims 1 to 7, the system comprises: The spectrum capture module starts based on the production line, adjusts the position and sensitivity of the spectrometer and captures the spectrum data emitted from the PVC pellets, records the light intensity and wavelength distribution data, and obtains the spectrum characteristic value; The data analysis and control module uses the spectral characteristic values ​​to perform quantitative processing on the spectral data, calculates the light intensity distribution and wavelength changes, compares the real-time data with the historical data, adjusts the light source intensity and reaction temperature, verifies the spectral data, and establishes the adjusted control parameters; The parameter optimization feedback module captures spectral data through the adjusted control parameters, compares the changes in spectral data before and after the adjustment, analyzes the adjustment effect, and constructs a parameter optimization effect record; The status update and adjustment module calculates the chemical agent delivery rate and heater power adjustment value based on the parameter optimization effect record, adjusts the equipment settings in real time, automatically updates the production status, and generates real-time production line control results; The abnormal monitoring and maintenance module monitors the real-time control results of the production line, identifies deviations and abnormalities, records and diagnoses abnormal conditions, adjusts production parameters and equipment maintenance strategies, and obtains the operating status results after recovery.

Images