One-key production control method and system for mixed emulsion explosive

Abstract

The application discloses a one-key production control method and system for mixed emulsion explosive, and relates to the field of automation and intelligent control. The application solves the problems of low efficiency, high cost, quality fluctuation and process uncertainty in the production of traditional mixed emulsion explosive through automation and intelligent control means. The application realizes accurate feeding of raw materials by using a quality sensor array and a PID control algorithm, ensures the stability of production parameters through multi-sensor data fusion and advanced control algorithm, and further improves the consistency of product quality. At the same time, a feedback control loop and a continuous learning mechanism are established to realize closed-loop control of the production process, optimize process parameters, ensure production stability and reliability, significantly improve production efficiency and product quality, and reduce labor costs.

Description

TECHNICAL FIELD

[0001] The application relates to the field of automation and intelligent control, in particular to a one-key production control method and system for mixed emulsion explosive. BACKGROUND

[0002] As the core material of modern industrial blasting, mixed emulsion explosive plays an irreplaceable role in the fields of mining, infrastructure construction and civil engineering. With the acceleration of industrialization and the continuous improvement of safety production requirements, higher standards are put forward for the precise control and automation level of the production process of mixed emulsion explosive. The traditional production method of mixed emulsion explosive mainly relies on manual operation and semi-automatic equipment, which has problems such as low production efficiency, high labor cost and large product quality fluctuation. Existing automation solutions can only realize automatic control of local links, lack unified management and coordination of the whole production process, and are difficult to meet the needs of modern production.

[0003] In the production process of mixed emulsion explosive, the accurate control of raw material ratio directly affects the performance and safety of the product. Liquid ammonium nitrate, diesel oil and emulsifier and other raw materials need to be mixed according to strict proportions. Any slight deviation may cause significant changes in product quality. When the raw material ratio cannot be accurately and automatically controlled, the key parameters such as temperature, pressure and flow in the production process are also difficult to maintain stable state. This parameter fluctuation further aggravates the uncertainty of the production process, so that the whole production process cannot form an effective closed-loop control system. SUMMARY

[0004] The purpose of the present application is to provide a one-key production control method and system for mixed emulsion explosive, which realizes the full-process automation and closed-loop control of mixed emulsion explosive production through automation and intelligent control means.

[0005] The purpose of the present application can be achieved by the following technical solutions:

[0006] The present application provides a one-key production control method for mixed emulsion explosive, comprising the following steps:

[0007] Real-time quality data of liquid ammonium nitrate, diesel oil and emulsifier are obtained. The weight change information of each raw material tank is collected through a quality sensor array. The target feeding amount is calculated according to the preset ratio parameters. According to the single material independent pipeline conveying logic, the accurate feeding time sequence and independent feeding rate control instructions of each raw material are determined;

[0008] The proportional-integral-derivative control algorithm is started according to the independent feeding control instructions. The flow output of each raw material pipeline is adjusted separately through electromagnetic valve group and variable frequency pump station. The actual feeding flow data is monitored by Coriolis mass flowmeter. Stable single material flow precision control is obtained through single pipeline closed-loop control.

[0009] Combined with single-pipeline flow control effect, start fuzzy control algorithm to adjust power output of steam indirect heating system and cooling system, dynamically match raw material characteristics, and determine optimal temperature control strategy parameters;

[0010] Adopt pressure transmitter array to monitor pressure change trend of reaction kettle and material pipeline and steam pipeline; according to temperature control parameters and pressure change, calculate system pressure balance point, and maintain pressure stability of auxiliary pipeline through pressure regulating valve group and safety pressure relief device;

[0011] According to raw material sequence, pump into reaction kettle through independent pipeline; after each batch of raw material is pumped, start stirring motor frequency control system, adjust stirring speed and time according to raw material mixing progress; adopt torque sensor to monitor stirring resistance change, and determine mixing process completion when resistance curve tends to be stable, and determine mixing process completion signal;

[0012] Through online viscometer and densimeter, collect physical property parameters of mixed material; according to mixing process completion signal and physical property parameter data, start Kalman filter algorithm, filter noise from measurement data and evaluate state, and automatically generate product quality evaluation result.

[0013] Further, determine accurate raw material feeding time sequence and independent feeding rate control instruction, specifically including:

[0014] Obtain real-time weight data of liquid ammonium nitrate storage tank, diesel storage tank and emulsifier storage tank, and obtain stable storage tank mass change sequence;

[0015] According to storage tank mass change sequence and historical consumption record, adopt linear regression algorithm to establish material consumption prediction model of each storage tank, calculate material demand in future time window, automatically trigger replenishment signal when remaining available time of storage tank is lower than preset safety threshold, start material replenishment process, and obtain storage tank replenishment state identifier;

[0016] According to preset mass ratio parameters of liquid ammonium nitrate, diesel and emulsifier, and combined with target output of current production batch, calculate accurate feeding mass demand of each raw material, and then adopt current mass state of storage tank and standard feeding formula data to determine actual feedable amount of each raw material through material balance calculation, and obtain feeding execution scheme;

[0017] According to feeding execution scheme and physical property parameters of each raw material, adopt PID control algorithm to calculate optimal feeding rate, and determine feeding start time and feeding duration, and obtain detailed feeding time sequence control parameters;

[0018] Drive each storage tank discharge valve and metering pump system through feeding time sequence control parameters, monitor mass flow change in feeding process in real time, and obtain accurate raw material ratio mixture.

[0019] Further, stable single-material flow precision control is obtained, specifically including:

[0020] Obtain the feeding control instruction, determine the independent target flow value of each raw material pipeline by analyzing the instruction data, initialize the proportional integral derivative control algorithm, calculate the initial opening of the electromagnetic valve group and the initial speed of the variable frequency pump station, and determine the flow regulation scheme;

[0021] Execute the flow regulation scheme through the electromagnetic valve group and the variable frequency pump station, and use the Coriolis mass flowmeter to collect real-time flow data of each raw material pipeline. When the deviation between the actual flow value and the target flow value exceeds the preset threshold, the pump station speed adjustment amount is recalculated through the proportional integral derivative control algorithm to obtain new speed control parameters;

[0022] Adjust the operating frequency of the variable frequency pump station to update the flow output of the raw material pipeline, and continuously monitor the adjusted actual flow data through the Coriolis mass flowmeter. When the deviation still exceeds the preset threshold, iteratively execute the proportional integral derivative control algorithm to determine the final stable matching flow;

[0023] Extract the flow trend of each raw material pipeline from the stable matching flow data, and predict future flow fluctuations through time series analysis to obtain a flow prediction model.

[0024] Further, determine the optimal temperature control strategy parameters, specifically including:

[0025] Obtain the feeding control instruction, determine the independent target flow value of each raw material pipeline by analyzing the instruction data, initialize the proportional integral derivative control algorithm, calculate the initial opening of the electromagnetic valve group and the initial parameters of the variable frequency pump station, and determine the single-pipeline flow regulation scheme;

[0026] Execute the single-pipeline flow regulation scheme through the electromagnetic valve group and the variable frequency pump station, and use the Coriolis mass flowmeter to collect real-time flow data of each raw material pipeline. When the deviation between the actual flow value and the corresponding pipeline target flow value exceeds the preset threshold, the regulation parameters are recalculated through the proportional integral derivative control algorithm to update the opening of the electromagnetic valve group and the output power of the pump station;

[0027] Continuously monitor the adjusted actual flow data. If the deviation still exceeds the threshold, iteratively execute the proportional integral derivative control algorithm until the flow of each pipeline stabilizes within the target value ±5% range, forming a stable flow sequence for single-pipeline independent control.

[0028] Further, maintain the pressure stability of the auxiliary pipeline through the pressure regulating valve group and the safety pressure relief device, specifically including:

[0029] The pressure transmitter array is used to obtain real-time pressure data from the reaction kettle and material pipelines and steam pipelines, and the Kalman filtering algorithm is used to filter out noise to obtain a standardized pressure data set.

[0030] According to the standardized pressure data set and the temperature control parameters, the pressure safety threshold of the auxiliary pipelines such as steam and compressed air is calculated, and the target pressure control range is set.

[0031] Real-time analysis of pressure change trend, when the steam / compressed air pipeline pressure rising rate exceeds the preset alarm threshold, generate pressure relief control signal to drive the safety relief device to open; when the pressure is in the normal fluctuation range, generate pressure regulating control signal to adjust the opening of the pressure regulating valve group, realize pressure closed loop control through valve position feedback;

[0032] According to the pressure response data, the PID control algorithm is used to dynamically adjust the parameters of the pressure regulating valve group and the pressure relief device to ensure that the auxiliary pipeline pressure is stable within the target range.

[0033] Continuous monitoring of pressure fluctuation, if it exceeds the target control range, recalculate the pressure balance point, if it is within the range, maintain the current parameters, realize the dynamic balance of the auxiliary pipeline pressure.

[0034] Further, the mixed process completion signal is determined, specifically including:

[0035] Get real-time monitoring data of pressure sensor and raw material feeding ratio data, get the current mixing progress state value through data fusion processing, and then calculate the frequency converter output frequency parameter according to the mixing progress state value and the preset process parameter table, and get the target speed value of the stirring motor;

[0036] Adjust the stirring motor speed to the target speed value through the frequency conversion control system, start the torque sensor data acquisition module synchronously, get the torque change data sequence in the stirring process, and then use the sliding window method to process the torque change data sequence in real time, calculate the torque fluctuation variance value in the preset time window, and get the current stirring resistance stability index;

[0037] When the stirring resistance stability index is less than the preset stability threshold, the support vector machine algorithm is used to comprehensively evaluate the pressure parameters, torque stability index and mixing time parameters to judge the mixing uniformity standard state.

[0038] According to the mixing uniformity standard state result, when the judgment result is up to standard, generate the mixed process completion signal and stop the stirring motor operation, when the judgment result is not up to standard, return to adjust the stirring speed and continue the mixing process, save the pressure parameter change curve, torque fluctuation data and final uniformity evaluation result in the mixing process through the data recording module, and form the process parameter optimization database.

[0039] Further, the product quality evaluation result is generated, specifically including:

[0040] The viscosity value and the density value of the mixture are synchronously collected by an online viscometer and a densimeter to obtain a real-time physical property parameter data set, and the physical property parameter data is arranged in time sequence according to a preset data collection frequency to obtain a continuous and complete measurement data sequence;

[0041] The measurement data sequence is processed by using a Kalman filtering algorithm, a mathematical model is established by using a state transition matrix and an observation matrix, and the physical property parameter estimated value is compared with a preset standard range in value, and when the viscosity value or the density value deviates from the upper and lower limits of the standard range, it is marked as an abnormal state to determine the process adjustment requirement;

[0042] The process parameter adjustment module is triggered by the abnormal state marking, the adjustment amplitude is calculated according to the deviation degree, the process adjustment instruction containing the temperature adjustment amount and the stirring speed correction value is generated, the adjusted physical property parameters are comprehensively evaluated by using a weighted scoring algorithm, the quality evaluation score is calculated according to the compliance of the viscosity value and the density value, and the product quality evaluation result is obtained;

[0043] According to the quality evaluation result, a product batch file is established to record the physical property parameter change track and the process adjustment history, and a quality traceability database is formed.

[0044] Further, after obtaining the product quality evaluation result, further including: establishing a feedback control loop according to the product quality evaluation result, calculating a process parameter optimization scheme through a historical database and real-time monitoring data, outputting a qualified product signal when the quality index is qualified for three consecutive times, and backtracking the adjustment of raw material ratio and process parameters when the quality index is abnormal, forming a complete closed-loop control system operation state.

[0045] Further, a feedback control loop is established according to the product quality evaluation result, and a process parameter optimization scheme is calculated through a historical database and real-time monitoring data, specifically including:

[0046] The process parameter records and quality index data in the historical database are obtained to obtain a historical process data set, a support vector machine algorithm is used to train the historical process data set, a mapping relationship model between the process parameters and the quality index is established, and the influence weight of each process parameter on the quality index is determined;

[0047] Real-time monitoring data in the current production process are obtained through a sensor network to obtain a real-time process state parameter matrix, and the mapping relationship model trained is input according to the real-time process state parameter matrix to calculate a predicted quality index value and obtain a quality prediction result;

[0048] When the quality prediction result exceeds the preset qualified threshold value for three times in succession, a qualified product signal is automatically output and the current process parameter setting is continued, and when the quality prediction result is lower than the qualified threshold value, a parameter adjustment mechanism is triggered;

[0049] The particle swarm optimization algorithm is used for optimization calculation on the abnormal process parameters, a maximum quality index is used as an objective function, and the optimal raw material ratio and process parameter combination is searched within a constraint condition range to determine a parameter adjustment scheme;

[0050] The control instruction of the production equipment is updated according to the parameter adjustment scheme, and the adjusted process parameters and the corresponding quality index are stored in a historical database to form a closed-loop control system operation mechanism for continuous learning.

[0051] The application provides a one-key production control system for mixed emulsion explosive, which is used for realizing a one-key production control method for mixed emulsion explosive, and comprises the following steps:

[0052] A raw material feeding control module is used for collecting weight data of liquid ammonium nitrate, diesel and emulsifier storage tanks in real time through a mass sensor array, calculating the feeding amount of each raw material in combination with a preset ratio and a production target, predicting material consumption by using a linear regression algorithm, triggering an automatic feeding mechanism, independently adjusting the feeding rate of each raw material pipeline by using a PID control algorithm, and driving a valve and a metering pump to accurately feed;

[0053] A flow dynamic adjustment module is used for independently adjusting the flow of each raw material pipeline by using an electromagnetic valve group and a variable frequency pump station after receiving a feeding control instruction, monitoring the actual flow in real time by using a Coriolis mass flowmeter, dynamically correcting the flow deviation based on a PID control algorithm, obtaining stable ratio flow control through iterative adjustment, and establishing a flow prediction model to predict fluctuation trends;

[0054] A temperature intelligent control module is used for collecting temperature distribution data in a reaction kettle through a temperature sensor network, calculating a temperature gradient change rate, starting a fuzzy control algorithm to automatically adjust the power output of a steam indirect heating system and a cooling system when the gradient is abnormal, dynamically matching the characteristics of raw materials, and optimizing the temperature distribution;

[0055] A pressure balance control module is used for monitoring the pressure of material pipelines and steam pipelines by using a pressure transmitter array, filtering noise by using a Kalman filtering algorithm, calculating the pressure safety threshold of a steam / compressed air pipeline, automatically starting a safety pressure relief device when the pressure rising rate exceeds a preset alarm threshold, and adjusting the opening degree of a pressure regulating valve group and correcting the pressure deviation by using a PID algorithm when the pressure fluctuates normally.

[0056] The mixed process control module pumps raw materials into the reaction kettle in sequence, starts the frequency conversion control system of the stirring motor immediately after each batch of raw materials is fed, and adopts low-speed stirring at the beginning to avoid splashing and switches to high-speed homogenization in the later period; the stirring resistance data are collected in real time through the torque sensor, the sliding window algorithm is used to calculate the standard deviation of torque fluctuation, and when the data of 3 consecutive windows are less than the stable threshold and reach the preset stirring time, it is determined that the mixing is up to standard and a completion signal is generated;

[0057] The quality evaluation and closed-loop control module collects material physical property parameters through an online viscometer and a densimeter, filters out noise and evaluates the index using Kalman filtering algorithm, triggers process adjustment instructions when the parameters are abnormal, and builds a quality prediction model based on historical data and support vector machine, and optimizes parameters through a particle swarm optimization algorithm.

[0058] The present application has the following advantages:

[0059] Through automatic and intelligent control means, the whole-process automatic control of mixed emulsion explosive production is realized, the weight change of the raw material storage tank is monitored in real time through the quality sensor array, the feeding amount and feeding time sequence of each raw material are accurately calculated in combination with the preset proportioning parameters and the target output, the feeding rate is optimized using the PID control algorithm, and the accuracy of the raw material proportioning is ensured, which not only solves the problems of low production efficiency and high labor cost caused by relying on manual operation in the traditional production method, but also significantly improves the production efficiency, reduces the manual intervention and reduces the labor cost.

[0060] The present application realizes real-time monitoring and dynamic adjustment of key parameters in the production process through multi-sensor data fusion and advanced control algorithms, accurately controls the temperature distribution in the reaction kettle through a temperature sensor network and a fuzzy control algorithm, ensures the uniformity and stability of the temperature, and at the same time, dynamically maintains the stable state of the system pressure through a pressure transmitter array and a PID control algorithm, effectively solves the problem of unstable product quality caused by parameter fluctuation in the traditional production method, and improves the consistency and stability of product quality.

[0061] Through the establishment of a feedback control loop and a continuous learning mechanism, closed-loop control of the production process is realized, the physical property parameters of the mixed material are collected in real time through an online viscometer and a densimeter, the data are filtered and the state is estimated using Kalman filtering algorithm, the product quality evaluation result is generated, and the optimal raw material proportioning and process parameter combination are searched through a particle swarm optimization algorithm, and the control instructions of the production equipment are updated, which not only solves the problem of production process uncertainty caused by lack of unified management and coordination in the traditional production method, but also optimizes the process parameters through the continuous learning mechanism, forms a complete closed-loop control system, and ensures the stability and reliability of the production process. BRIEF DESCRIPTION OF DRAWINGS

[0062] For better understanding and implementation, the technical solutions of the present application are described in detail below with reference to the drawings.

[0063] Figure 1 The flowchart of the one-key production control method of the mixed loading emulsion explosive provided for Embodiment 1 of the present application is shown in the figure.

[0064] Figure 2 The flowchart of determining the accurate feeding time sequence and independent feeding rate control instructions of each raw material of the one-key production control method of the mixed loading emulsion explosive provided for Embodiment 1 of the present application is shown in the figure.

[0065] Figure 3 The flowchart of obtaining the product quality evaluation result of the one-key production control method of the mixed loading emulsion explosive provided for Embodiment 1 of the present application is shown in the figure.

[0066] Figure 4 The structural schematic diagram of the one-key production control system of the mixed loading emulsion explosive provided for Embodiment 2 of the present application is shown in the figure. DETAILED DESCRIPTION

[0067] To further illustrate the technical means and effects adopted by the present application to achieve the predetermined application purposes, exemplary embodiments will be described in detail herein, which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all the embodiments consistent with the present application. Instead, they are merely examples of methods and systems consistent with some aspects of the present application as detailed in the appended claims.

[0068] The terms used in the present application are merely for the purpose of describing specific embodiments and are not intended to limit the present application. The singular forms "a", "an" and "the" used in the present application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used herein means and includes any or all possible combinations of one or more associated listed items.

[0069] The specific embodiments, features and effects according to the present application are described in detail below in combination with the drawings and preferred embodiments.

[0070] Embodiment 1

[0071] Please refer to Figures 1-3 The present embodiment provides a one-key production control method of mixed loading emulsion explosive, which comprises the following steps:

[0072] S1, obtaining real-time quality data of liquid ammonium nitrate, diesel and emulsifier, collecting weight change information of each raw material tank through a quality sensor array, calculating target feeding quantity according to preset proportioning parameters, determining accurate feeding time sequence and independent feeding rate control instruction of each raw material according to single material independent pipeline conveying logic;

[0073] Further, the accurate feeding time sequence and independent feeding rate control instruction of each raw material are determined, specifically including:

[0074] S11, obtaining real-time weight data of liquid ammonium nitrate tank, diesel tank and emulsifier tank collected by the quality sensor array, filtering out sensor noise interference through a data preprocessing module to obtain a stable tank mass change sequence;

[0075] S12, establishing a material consumption prediction model of each tank by using a linear regression algorithm according to the tank mass change sequence and historical consumption record, calculating the material demand in a future time window to obtain the remaining available time of each tank, and when the remaining available time of the tank is lower than a preset safety threshold, automatically triggering a replenishment signal of the corresponding tank, starting a material replenishment process through a replenishment control system to obtain a tank replenishment state identifier;

[0076] S13, calculating the accurate feeding quality demand of each raw material according to the preset quality proportioning parameters of liquid ammonium nitrate, diesel and emulsifier, combining the target output of the current production batch to obtain standard feeding formula data, and then using the current quality state of the tank and the standard feeding formula data to determine the actual feedable quantity of each raw material through material balance calculation, and generating a feeding permission identifier when the actual feedable quantity meets the formula requirement to obtain a feeding execution scheme;

[0077] S14, calculating the optimal feeding rate of liquid ammonium nitrate, diesel and emulsifier by using a PID control algorithm according to the feeding execution scheme and the physical property parameters of each raw material, and determining the feeding start time and feeding duration to obtain detailed feeding time sequence control parameters; wherein the feeding rate of each raw material pipeline is independently controlled, and only one kind of raw material is conveyed in a single pipeline;

[0078] S15, driving each tank outlet valve and metering pump system through the feeding time sequence control parameters, and each raw material is sequentially pumped into the reaction kettle through independent pipelines in the order of “liquid ammonium nitrate→diesel→emulsifier”, and the quality flow change in the feeding process is monitored in real time to obtain an accurate raw material proportioning mixture.

[0079] Specifically, through precise monitoring and intelligent control, accurate feeding of raw materials in mixed emulsion explosive production is realized, the continuity and stability of production are ensured, the product quality and safety are improved, the production cost and manual intervention are reduced, and the production efficiency is improved.

[0080] S2, start the proportional-integral-derivative (PID) control algorithm according to the independent feeding control instruction, and independently adjust the flow output of each raw material pipeline (such as the liquid ammonium nitrate pipeline) through the electromagnetic valve group and the variable frequency pump station; real-time monitoring of the actual feeding flow data of each pipeline is performed by using the Coriolis mass flowmeter, and stable single material flow precision control is obtained through single pipeline closed loop control, avoiding the cooperation of multiple material pipelines;

[0081] Further, stable single material flow precision control is obtained, specifically including:

[0082] The feeding control instruction is obtained, the independent target flow value of each raw material pipeline (not involving the matching ratio) is determined by analyzing the instruction data, and then the proportional-integral-derivative control algorithm is initialized to calculate the initial opening of the electromagnetic valve group and the initial speed of the variable frequency pump station, and determine the flow regulation scheme;

[0083] The flow regulation scheme is executed by the electromagnetic valve group and the variable frequency pump station, the actual flow data of each raw material pipeline is collected in real time by using the Coriolis mass flowmeter, and the actual flow value is obtained. When the deviation between the actual flow value and the target flow value exceeds the preset threshold value, the pump station speed adjustment amount is recalculated by the proportional-integral-derivative control algorithm to obtain new speed control parameters, and single pipeline flow closed loop control is realized;

[0084] The running frequency of the variable frequency pump station is adjusted to update the flow output of the raw material pipeline, and the adjusted actual flow data is obtained. The adjusted actual flow data is continuously monitored by the Coriolis mass flowmeter. When the deviation still exceeds the preset threshold value, the proportional-integral-derivative control algorithm is iteratively executed to determine the final stable matching flow;

[0085] The flow variation trend of each raw material pipeline is extracted from the stable matching flow data, and the future flow fluctuation is predicted by time series analysis to obtain a flow prediction model.

[0086] Specifically, by using the proportional-integral-derivative (PID) control algorithm, combined with the electromagnetic valve group and the variable frequency pump station, accurate regulation and stable control of the flow of each raw material pipeline are realized. Real-time monitoring by the Coriolis mass flowmeter ensures high precision and reliability of the flow data. Through iterative adjustment of the pump station speed, the system can quickly respond and correct the flow deviation, and finally realize stable raw material matching flow control. In addition, by predicting future flow fluctuations through time series analysis, the prediction ability and stability of the system are further improved, ensuring the continuity of the production process and the consistency of the product quality.

[0087] S3, combined with single pipeline flow control effect, start fuzzy control algorithm to adjust the power output of the steam indirect heating system (steam does not directly contact the material, the temperature is raised by heat conduction through the jacket or coil) and the cooling system, dynamically match the raw material characteristics (such as liquid ammonium nitrate crystallization temperature), determine the optimal temperature control strategy parameters (such as heating power, cooling start-stop threshold);

[0088] Further, determining the optimal temperature control strategy parameters specifically includes:

[0089] Obtain the feeding control instruction, determine the independent target flow value of each raw material pipeline (not involving the matching ratio) by analyzing the instruction data, initialize the proportional-integral-derivative (PID) control algorithm, calculate the initial parameters of the electromagnetic valve group opening and the frequency conversion pump station, and determine the single pipeline flow regulation scheme;

[0090] Execute the single pipeline flow regulation scheme through the electromagnetic valve group and the frequency conversion pump station, and use the Coriolis mass flowmeter to collect the actual flow data of each raw material pipeline in real time; when the deviation between the actual flow value and the target flow value of the corresponding pipeline exceeds the preset threshold, the adjustment parameters are recalculated through the PID control algorithm, the electromagnetic valve group opening and the pump station output power are updated, and the single pipeline flow closed-loop control is realized;

[0091] Continuously monitor the adjusted actual flow data, if the deviation still exceeds the threshold, iterate the PID algorithm until the flow of each pipeline stabilizes within the target value ±5% range, forming a stable flow sequence of single pipeline independent control.

[0092] Specifically, the temperature distribution in the reaction kettle is monitored in real time by the temperature sensor network, and the power output of the heating and cooling system is dynamically adjusted by the fuzzy control algorithm, which can effectively respond to the temperature gradient change, ensure the uniformity and stability of the temperature distribution, and automatically adjust the heating and cooling parameters when the temperature gradient change rate exceeds the safety threshold. Through iterative optimization, the optimality of the temperature control strategy is ensured, thereby improving the safety of the production process and the consistency of the product quality.

[0093] S4, use a pressure transmitter array to monitor the pressure change trend of the reaction kettle (normal pressure environment, no storage tank pressure control requirement) and the material pipeline, steam pipeline; according to the temperature control parameters and the pressure change, calculate the system pressure balance point (such as the steam pipeline pressure safety threshold), maintain the pressure stability of the auxiliary pipeline such as steam, compressed air through the pressure regulating valve group and the safety pressure relief device, ensure the safe operation of the reaction kettle under normal pressure;

[0094] Further, maintaining the pressure stability of the auxiliary pipeline such as steam, compressed air through the pressure regulating valve group and the safety pressure relief device specifically includes:

[0095] The pressure transmitter array is used to acquire real-time pressure data from the reaction kettle (atmospheric environment, no pressure control requirement) and material pipelines and steam pipelines, the Kalman filtering algorithm is used to filter out noise, and a standardized pressure data set is obtained.

[0096] According to the standardized pressure data set and the temperature control parameters, the pressure safety threshold (i.e., the system pressure balance point) of the auxiliary pipelines such as steam and compressed air is calculated, and the target pressure control range is set.

[0097] Real-time analysis of pressure change trend, when the steam / compressed air pipeline pressure rise rate exceeds the preset alarm threshold, generate pressure relief control signal to drive the safety relief device to open; when the pressure is in the normal fluctuation range, generate pressure regulating control signal to adjust the opening degree of the pressure regulating valve group, realize pressure closed loop control through valve position feedback;

[0098] According to the pressure response data (such as the pressure drop rate after pressure relief, the pressure stable value after pressure regulation), the PID control algorithm is used to dynamically adjust the parameters of the pressure regulating valve group and the pressure relief device, to ensure that the auxiliary pipeline pressure is stable in the target range (such as steam pressure ≤0.3MPa);

[0099] Continuous monitoring of pressure fluctuation, if it exceeds the target control range, recalculate the pressure balance point, if it is within the range, maintain the current parameters, realize the dynamic balance of the auxiliary pipeline pressure.

[0100] Specifically, real-time pressure data is collected by a pressure transmitter array and Kalman filtering algorithm is used to filter out noise, combined with temperature control parameters to accurately calculate the pressure safety threshold and set the target pressure control range. The system analyzes the pressure change trend in real time, opens the safety relief device when the alarm threshold is exceeded, adjusts the opening degree of the pressure regulating valve group to realize closed loop control when the pressure fluctuates normally, and dynamically adjusts the parameters according to the pressure response data to ensure that the auxiliary pipeline pressure is stable in the target range, realizing dynamic balance. This process effectively prevents system overpressure, ensures production safety, optimizes production process, improves product quality stability, and reduces safety risks.

[0101] S5, in the order of "liquid ammonium nitrate → diesel → emulsifier", sequentially pump into the reaction kettle through independent pipelines, start the frequency control system of the stirring motor after each batch of material is added, adjust the stirring speed and time according to the mixing progress of the raw materials (such as initial low-speed stirring to avoid splashing, high-speed homogenization in later period); use a torque sensor to monitor the change of stirring resistance, when the resistance curve tends to be stable, determine that the mixing process is completed, and determine the mixing process completion signal;

[0102] Further, the mixing process completion signal is determined, specifically including:

[0103] The system acquires real-time monitoring data from pressure sensors and raw material feeding ratio data. Through data fusion processing, it obtains the current mixing progress status value. Based on the mixing progress status value and the preset process parameter table, it uses a PID control algorithm to calculate the inverter output frequency parameter and obtain the target speed value of the stirring motor.

[0104] The variable frequency control system adjusts the speed of the stirring motor to the target speed value, and the torque sensor data acquisition module is started simultaneously to obtain the torque change data sequence during the stirring process. Then, the sliding window method is used to process the torque change data sequence in real time, calculate the torque fluctuation variance value within the preset time window, and obtain the current stirring resistance stability index.

[0105] When the stirring resistance stability index is less than the preset stability threshold, the support vector machine algorithm is used to comprehensively evaluate the pressure parameter, torque stability index and mixing time parameter to determine the mixing uniformity status.

[0106] Based on the results of the mixing uniformity standard, if the result is satisfactory, a mixing process completion signal is generated and the stirring motor stops running; if the result is unsatisfactory, the mixing process is resumed by adjusting the stirring speed. The pressure parameter change curve, torque fluctuation data and final uniformity evaluation results during the mixing process are saved through the data recording module, forming a process parameter optimization database.

[0107] Specifically, through the coordinated operation of the variable frequency control system for the stirring motor and the torque sensor, precise control of the stirring process and real-time monitoring of mixing uniformity are achieved. Based on the dynamic equilibrium state of pressure parameters and the mixing progress of raw materials, the stirring speed and time are dynamically adjusted to ensure the efficiency and uniformity of the mixing process. The stability index of stirring resistance is evaluated using a sliding window method and machine learning algorithms (support vector machines) to accurately determine whether the mixing uniformity meets the standards, and a mixing process completion signal is generated accordingly. This process not only improves the level of automation in production but also provides data support for continuous optimization of process parameters through the data recording module, thereby enhancing the stability and consistency of product quality.

[0108] S6. Collect the physical property parameters of the mixture through online viscometers and densitometers, and start the Kalman filter algorithm based on the mixing process completion signal and physical property parameter data to filter out noise and evaluate the condition of the measurement data, and automatically generate product quality evaluation results.

[0109] Furthermore, product quality assessment results are generated, specifically including:

[0110] S61, synchronously collect viscosity and density values of the mixture by an online viscosity meter and a density meter, obtain a real-time physical property parameter data set, arrange the physical property parameter data in time sequence according to a preset data collection frequency, trigger a data compensation mechanism when a data collection interval exceeds a preset time threshold, and obtain a continuous and complete measurement data sequence;

[0111] S62, process the measurement data sequence by using a Kalman filtering algorithm, establish a mathematical model through a state transition matrix and an observation matrix, obtain a noise-filtered physical property parameter estimated value, and compare the physical property parameter estimated value with a preset standard range, mark as an abnormal state when the viscosity value or the density value deviates from the upper and lower limits of the standard range, and determine a process adjustment requirement;

[0112] S63, trigger a process parameter adjustment module through the abnormal state marking, calculate an adjustment amplitude according to a deviation degree, generate a process adjustment instruction containing a temperature adjustment amount and a stirring speed correction value, comprehensively evaluate the adjusted physical property parameters by using a weighted scoring algorithm, calculate a quality evaluation score according to the compliance of the viscosity value and the density value, and obtain a product quality evaluation result;

[0113] S64, establish a product batch file according to the quality evaluation result, record a physical property parameter change track and a process adjustment history, and form a quality traceability database.

[0114] Specifically, the physical property parameters of the mixture are collected in real time by the online viscosity meter and the density meter, and the Kalman filtering algorithm is used to filter noise and estimate the state of the data, so that the key indicators of product quality can be accurately monitored. When the physical property parameters deviate from the preset standard range, the process adjustment instruction is automatically triggered, the adjustment amplitude is calculated, and a specific process adjustment scheme is generated, so that the product quality meets the standard. In addition, the adjusted physical property parameters are comprehensively evaluated by using the weighted scoring algorithm, the quality evaluation score is calculated, and finally the product quality evaluation result is formed. This process not only improves the stability and consistency of product quality, but also provides strong support for the optimization and quality control of the production process by establishing the product batch file and the quality traceability database.

[0115] Further, it also includes that the raw material conveying pipeline is configured with a cleaning and purging system, when a production batch switching signal or a shutdown instruction is detected, a steam purging program is automatically executed (purging is performed by connecting the material pipeline with a steam pipeline), and residual materials in the pipeline are removed; at the same time, a safety interlock is triggered to ensure that the system enters a standby state after purging is completed.

[0116] Further, after obtaining the product quality evaluation result, a feedback control loop is established according to the product quality evaluation result, a process parameter optimization scheme is calculated through a historical database and real-time monitoring data, a qualified product signal is output when the quality index is qualified for three consecutive times, and the raw material ratio and process parameters are adjusted back when the quality index is abnormal, thereby forming a complete closed-loop control system operation state.

[0117] Further, a feedback control loop is established according to the product quality evaluation result, a process parameter optimization scheme is calculated through a historical database and real-time monitoring data, and specifically includes:

[0118] The process parameter records and quality index data in the historical database are obtained to obtain a historical process data set, a support vector machine algorithm is used to train the historical process data set, a mapping relationship model between the process parameters and the quality index is established, and the influence weight of each process parameter on the quality index is determined;

[0119] Real-time monitoring data in the current production process are obtained through a sensor network, including temperature, pressure, flow rate and raw material ratio information, a real-time process state parameter matrix is obtained, and then the real-time process state parameter matrix is input into the trained mapping relationship model to calculate a predicted quality index value Q=f(T, P, F, R), wherein T represents a temperature parameter, P represents a pressure parameter, F represents a flow rate parameter, and R represents a raw material ratio parameter, thereby obtaining a quality prediction result;

[0120] When the quality prediction result exceeds a preset qualified threshold for three consecutive times, the system automatically outputs a qualified product signal and continues the current process parameter setting, and when the quality prediction result is lower than the qualified threshold, a parameter adjustment mechanism is triggered;

[0121] A particle swarm optimization algorithm is used to perform optimization calculation on the abnormal process parameters, a maximum quality index is used as an objective function, and an optimal raw material ratio and process parameter combination is searched within a constraint condition range to determine a parameter adjustment scheme;

[0122] The control instructions of the production equipment are updated according to the parameter adjustment scheme, and the adjusted process parameters and corresponding quality index are stored in the historical database, thereby forming a continuous learning closed-loop control system operation mechanism.

[0123] Specifically, through the feedback control loop and the advanced algorithm, the process parameters are dynamically optimized according to the product quality evaluation result, the mapping relationship model is established by using the historical data and real-time monitoring, the quality index is predicted and the parameters are automatically adjusted, the closed-loop control is formed, the stability and consistency of the product quality are improved, and the production efficiency and intelligent level are improved through the continuous learning mechanism to optimize the process parameters.

[0124] Embodiment 2

[0125] Please refer toFigure 4 The embodiment provides a one-key production control system of mixed emulsion explosive, which is used for realizing a one-key production control method of mixed emulsion explosive, and comprises the following modules.

[0126] A raw material feeding control module acquires weight data of liquid ammonium nitrate, diesel and emulsifier storage tanks in real time through a mass sensor array, calculates the feeding amount of each raw material in combination with preset proportions and production targets, predicts material consumption by using a linear regression algorithm, triggers an automatic feeding mechanism, independently adjusts the feeding rate of each raw material pipeline by using a PID control algorithm, drives valves and metering pumps to accurately feed, and ensures the accuracy of raw material proportioning.

[0127] A flow dynamic adjustment module independently adjusts the flow of each raw material pipeline (such as the liquid ammonium nitrate, diesel and emulsifier pipelines) through an electromagnetic valve group and a frequency conversion pump station after receiving a feeding control instruction, monitors the actual flow in real time by using a Coriolis mass flowmeter, dynamically corrects the flow deviation based on a PID control algorithm, realizes stable proportioning flow control through iterative adjustment, and establishes a flow prediction model to predict fluctuation trends.

[0128] A temperature intelligent control module acquires temperature distribution data in a reaction kettle through a temperature sensor network, calculates the temperature gradient change rate, starts a fuzzy control algorithm to automatically adjust the power output of a steam indirect heating system (steam passes through a jacket / coil heat conduction) and a cooling system when the gradient is abnormal, dynamically matches the characteristics of raw materials (such as the crystallization temperature of liquid ammonium nitrate), optimizes temperature distribution, and ensures uniform and stable reaction temperature.

[0129] A pressure balance control module monitors the pressure of material pipelines and steam pipelines (the reaction kettle is under normal pressure, and there is no pressure control requirement) by using a pressure transmitter array, filters noise by using a Kalman filtering algorithm, calculates the pressure safety threshold (system pressure balance point) of the steam / compressed air pipeline, automatically opens a safety pressure relief device when the pressure rising rate exceeds a preset alarm threshold, adjusts the opening degree of a pressure regulating valve group when there is normal fluctuation, corrects the pressure deviation by using a PID algorithm, and ensures that the pressure of the auxiliary pipeline is stably in a target range (such as the steam pressure ≤0.3 MPa).

[0130] The mixed process control module sequentially pumps into the reaction kettle in the order of "liquid ammonium nitrate→diesel→emulsifier". After each batch of material is fed, the frequency control system of the stirring motor is started immediately. The initial low-speed stirring (such as 50 rpm) is adopted to avoid splashing, and the high-speed homogenization (such as 150 rpm) is switched to in the later period. The stirring resistance data are collected in real time through the torque sensor, the sliding window algorithm is used to calculate the standard deviation of torque fluctuation, when the data of 3 consecutive windows are less than the stable threshold (such as 0.5 N·m) and the preset stirring time (such as 15 min) is reached, it is determined that the mixing is up to the standard and the completion signal is generated. If it is not up to the standard, the stirring time is automatically prolonged or the rotating speed is adjusted, the pressure data and the support vector machine evaluation logic are removed, and only the torque stability and the time parameter are relied on to independently transport the single material through the single material pipeline.

[0131] The quality evaluation and closed-loop control module collects material physical property parameters through an online viscometer and a densimeter, filters out noise and evaluates indexes by using Kalman filtering algorithm, triggers process adjustment instructions (such as temperature and stirring speed correction) when the parameters are abnormal, and builds a quality prediction model based on historical data and a support vector machine. The particle swarm optimization algorithm is used to optimize parameters to form a closed-loop control system of "detection-adjustment-learning", and ensure the stability of product quality.

[0132] The above is only a preferred embodiment of the present application, and does not limit the present application in any form. Although the present application has been disclosed as above, it is not intended to limit the present application. Any person skilled in the art can make some changes or modifications to the above disclosed technical content to form equivalent embodiments with equivalent changes, without departing from the scope of the technical solution of the present application. Any modification, equivalent change and modification of the above embodiments made according to the technical essence of the present application, without departing from the technical solution of the present application, are still within the scope of the technical solution of the present application.

Claims

1. A one-click production control method for mixed emulsion explosives, characterized in that: Includes the following steps: Real-time quality data of liquid ammonium nitrate, diesel and emulsifier are obtained. Weight change information of each raw material storage tank is collected through a mass sensor array. The target feed amount is calculated according to the preset ratio parameters. The material is transported through an independent pipeline. The precise feeding sequence and independent feeding rate control command of each raw material are determined. The proportional-integral-derivative control algorithm is activated based on the independent feeding control command. The flow output of each raw material pipeline is adjusted individually through the solenoid valve group and the variable frequency pump station. The actual feeding flow data is monitored by the Coriolis mass flow meter. Stable single material flow accuracy control is obtained through single pipeline closed-loop control. By combining the effect of single-pipe flow control, a fuzzy control algorithm is activated to adjust the power output of the steam indirect heating system and cooling system, dynamically match the characteristics of raw materials, and determine the optimal temperature control strategy parameters. Determining the optimal temperature control strategy parameters includes: Obtain feeding control commands, determine the independent target flow values ​​of each raw material pipeline by parsing the command data, initialize the proportional-integral-derivative control algorithm, calculate the opening degree of the solenoid valve group and the initial parameters of the variable frequency pump station, and determine the single pipeline flow regulation scheme. A single-pipeline flow regulation scheme is implemented by using solenoid valve groups and variable frequency pump stations. Coriolis mass flow meters are used to collect the actual flow data of each raw material pipeline in real time. When the actual flow value deviates from the target flow value of the corresponding pipeline beyond the preset threshold, the regulation parameters are recalculated by proportional-integral-derivative control algorithm to update the opening degree of the solenoid valve group and the output power of the pump station. The actual flow data after adjustment is continuously monitored. If the deviation still exceeds the threshold, the proportional-integral-derivative control algorithm is iteratively executed until the flow of each pipeline is stable within ±5% of the target value, forming a stable flow sequence for independent control of a single pipeline. A pressure transmitter array is used to monitor the pressure change trends of the reactor, material pipelines, and steam pipelines; based on temperature control parameters and pressure changes, the system pressure balance point is calculated, and the pressure of the auxiliary pipelines is maintained stable through pressure regulating valve groups and safety pressure relief devices; Raw materials are pumped into the reactor through independent pipelines in sequence. After each batch of materials is added, the frequency conversion control system of the stirring motor is started to adjust the stirring speed and time according to the mixing progress of the raw materials. A torque sensor is used to monitor the change of stirring resistance. When the resistance curve tends to stabilize, the mixing process is determined to be completed, and the mixing process completion signal is determined. The physical properties of the mixture are collected by online viscometers and densitometers. Based on the mixing process completion signal and physical property data, a Kalman filter algorithm is activated to filter out noise and assess the condition of the measurement data, thereby obtaining the product quality assessment results.

2. The one-click production control method for mixed emulsion explosives according to claim 1, characterized in that: Determine the precise feeding sequence and independent feeding rate control commands for each raw material, specifically including: Real-time weight data of liquid ammonium nitrate storage tanks, diesel storage tanks, and emulsifier storage tanks were obtained to obtain a stable sequence of tank mass changes; Based on the tank quality change sequence and historical consumption records, a linear regression algorithm is used to establish a material consumption prediction model for each tank, calculate the material demand within the future time window, and automatically trigger a replenishment signal when the remaining available time of the tank is lower than the preset safety threshold, start the material replenishment process, and obtain the tank replenishment status identifier. Based on the preset mass ratio parameters of liquid ammonium nitrate, diesel oil and emulsifier, combined with the target output of the current production batch, the precise feeding mass requirements of each raw material are calculated. Then, using the current mass status of the storage tank and the standard feeding formula data, the actual feedable amount of each raw material is determined through material balance calculation, and the feeding execution plan is obtained. Based on the feeding execution plan and the physical characteristic parameters of each raw material, the optimal feeding rate is calculated using a PID control algorithm. At the same time, the feeding start time and feeding duration are determined to obtain detailed feeding sequence control parameters. By controlling the feeding timing parameters to drive the discharge valves and metering pump systems of each storage tank, the changes in mass flow rate during the feeding process are monitored in real time to obtain an accurate raw material ratio mixture.

3. The one-click production control method for mixed emulsion explosives according to claim 1, characterized in that: To achieve stable single-material flow rate accuracy control, specifically including: Obtain feeding control commands, determine the independent target flow values ​​of each raw material pipeline by parsing the command data, then initialize the proportional-integral-derivative control algorithm, calculate the opening degree of the solenoid valve group and the initial speed of the variable frequency pump station, and determine the flow regulation scheme. The flow regulation scheme is implemented by solenoid valve group and variable frequency pump station. The actual flow data is collected in real time by Coriolis mass flow meter. When the deviation between the actual flow value and the target flow value exceeds the preset threshold, the pump station speed adjustment is recalculated by proportional integral derivative control algorithm to obtain new speed control parameters. By adjusting the operating frequency of the variable frequency pump station, the flow output of the raw material pipeline is updated, and the actual flow data after adjustment is continuously monitored by the Coriolis mass flow meter. When the deviation still exceeds the preset threshold, the proportional integral derivative control algorithm is iteratively executed to determine the final stable proportion flow. The flow rate change trend of each raw material pipeline is extracted from the stable ratio flow rate data, and the future flow rate fluctuation is predicted by time series analysis to obtain the flow rate prediction model.

4. The one-click production control method for mixed emulsion explosives according to claim 1, characterized in that: The pressure in the auxiliary pipeline is maintained stable through a pressure regulating valve assembly and a safety relief device, specifically including: A pressure transmitter array is used to acquire real-time pressure data from the reactor, material pipelines, and steam pipelines. Noise is filtered out using a Kalman filter algorithm to obtain a standardized pressure dataset. Based on the standardized pressure dataset and temperature control parameters, calculate the pressure safety threshold of the auxiliary pipeline and set the target pressure control range; The system analyzes pressure change trends in real time. When the rate of pressure rise in the steam / compressed air pipeline exceeds the preset alarm threshold, it generates a pressure relief control signal to drive the safety pressure relief device to open. When the pressure is within the normal fluctuation range, it generates a pressure regulating control signal to adjust the opening of the pressure regulating valve group. Pressure closed-loop control is achieved through valve position feedback. Based on the pressure response data, the parameters of the pressure regulating valve group and the pressure relief device are dynamically adjusted using a PID control algorithm to ensure that the pressure in the auxiliary pipeline remains stable within the target range. Continuously monitor pressure fluctuations. If the pressure exceeds the target control range, recalculate the pressure balance point. If it is within the range, maintain the current parameters to achieve dynamic balance of auxiliary pipeline pressure.

5. The one-click production control method for mixed emulsion explosives according to claim 1, characterized in that: Determine the completion signal of the mixing process, specifically including: The system acquires real-time monitoring data from pressure sensors and raw material feeding ratio data. Through data fusion processing, it obtains the current mixing progress status value. Based on the mixing progress status value and the preset process parameter table, it uses a PID control algorithm to calculate the inverter output frequency parameter and obtain the target speed value of the stirring motor. The variable frequency control system adjusts the speed of the stirring motor to the target speed value, and the torque sensor data acquisition module is started simultaneously to obtain the torque change data sequence during the stirring process. Then, the sliding window method is used to process the torque change data sequence in real time, calculate the torque fluctuation variance value within the preset time window, and obtain the current stirring resistance stability index. When the stirring resistance stability index is less than the preset stability threshold, the support vector machine algorithm is used to comprehensively evaluate the pressure parameter, torque stability index and mixing time parameter to determine the mixing uniformity status. Based on the results of the mixing uniformity standard, if the result is satisfactory, a mixing process completion signal is generated and the stirring motor stops running; if the result is unsatisfactory, the mixing process is resumed by adjusting the stirring speed. The pressure parameter change curve, torque fluctuation data and final uniformity evaluation results during the mixing process are saved through the data recording module, forming a process parameter optimization database.

6. The one-click production control method for mixed emulsion explosives according to claim 1, characterized in that: The product quality assessment results include: Viscosity and density values ​​of the mixture are collected simultaneously by online viscometer and densitometer to obtain a real-time physical property parameter data set. The physical property parameter data are then arranged in time series according to the preset data acquisition frequency to obtain a continuous and complete measurement data sequence. The Kalman filter algorithm is used to process the measurement data sequence. A mathematical model is established through the state transition matrix and the observation matrix. Then, the estimated values ​​of physical property parameters are compared with the preset standard range. When the viscosity or density value deviates from the upper or lower limit of the standard range, it is marked as an abnormal state, and the process adjustment needs are determined. The process parameter adjustment module is triggered by an abnormal state flag. The adjustment range is calculated based on the degree of deviation, and a process adjustment instruction containing temperature adjustment and stirring speed correction values ​​is generated. Then, a weighted scoring algorithm is used to comprehensively evaluate the adjusted physical property parameters. The quality assessment score is calculated based on the compliance of viscosity and density values, and the product quality assessment result is obtained. Based on the quality assessment results, product batch files are established to record the trajectory of changes in physical property parameters and the history of process adjustments, forming a quality traceability database.

7. The one-click production control method for mixed emulsion explosives according to claim 6, characterized in that: After obtaining the product quality assessment results, the process also includes: establishing a feedback control loop based on the product quality assessment results; calculating process parameter optimization schemes through historical databases and real-time monitoring data; outputting a qualified product signal when the quality indicators pass three consecutive tests; and adjusting the raw material ratio and process parameters backtracking when the quality indicators are abnormal, thus forming a complete closed-loop control system operation status.

8. The one-click production control method for mixed emulsion explosives according to claim 7, characterized in that: Based on the product quality assessment results, a feedback control loop is established, and process parameter optimization schemes are calculated using historical databases and real-time monitoring data. Specifically, this includes: Obtain process parameter records and quality index data from the historical database to obtain a historical process dataset. Use the support vector machine algorithm to train the historical process dataset, establish a mapping relationship model between process parameters and quality indicators, and determine the influence weight of each process parameter on the quality indicators. The real-time monitoring data of the current production process is acquired by the sensor network to obtain the real-time process status parameter matrix. Then, the real-time process status parameter matrix is ​​input into the trained mapping relationship model to calculate the predicted quality index value and obtain the quality prediction result. If the quality prediction result exceeds the preset qualified threshold three times in a row, a qualified product signal will be automatically output and the current process parameter settings will continue. If the quality prediction result is lower than the qualified threshold, the parameter adjustment mechanism will be triggered. The particle swarm optimization algorithm is used to optimize abnormal process parameters. With the maximization of quality index as the objective function, the optimal raw material ratio and process parameter combination are searched within the constraints to determine the parameter adjustment scheme. The control commands for the production equipment are updated according to the parameter adjustment plan, and the adjusted process parameters and corresponding quality indicators are stored in the historical database to form a continuous learning closed-loop control system operation mechanism.

9. A one-button production control system for mixed emulsion explosives, applied to the one-button production control method for mixed emulsion explosives as described in any one of claims 1-8, characterized in that: include: The raw material feeding control module collects the weight data of liquid ammonium nitrate, diesel, and emulsifier storage tanks in real time through a mass sensor array. It calculates the feeding amount of each raw material based on the preset ratio and production target, predicts material consumption using a linear regression algorithm, triggers an automatic feeding mechanism, and independently adjusts the feeding rate of each raw material pipeline through a PID control algorithm to drive valves and metering pumps for precise feeding. The flow dynamic adjustment module, after receiving the feeding control command, independently adjusts the flow of each raw material pipeline through the solenoid valve group and the frequency conversion pump station. It uses the Coriolis mass flow meter to monitor the actual flow in real time, and uses the PID control algorithm to dynamically correct the flow deviation. It obtains stable proportion flow control through iterative adjustment and establishes a flow prediction model to predict the fluctuation trend. The intelligent temperature control module collects temperature distribution data inside the reactor through a temperature sensor network, calculates the rate of change of temperature gradient, and when the gradient is abnormal, it activates a fuzzy control algorithm to automatically adjust the power output of the steam indirect heating system and cooling system, dynamically matching the characteristics of the raw materials and optimizing the temperature distribution. This includes: acquiring feeding control commands, determining the independent target flow values ​​of each raw material pipeline by parsing the command data, initializing the proportional-integral-derivative control algorithm, calculating the opening degree of the solenoid valve group and the initial parameters of the variable frequency pump station, and determining the flow regulation scheme for a single pipeline. A single-pipeline flow regulation scheme is implemented by using solenoid valve groups and variable frequency pump stations. Coriolis mass flow meters are used to collect the actual flow data of each raw material pipeline in real time. When the actual flow value deviates from the target flow value of the corresponding pipeline beyond the preset threshold, the regulation parameters are recalculated by proportional-integral-derivative control algorithm to update the opening degree of the solenoid valve group and the output power of the pump station. Continuously monitor the adjusted actual flow data. If the deviation still exceeds the threshold, iteratively execute the proportional-integral-derivative control algorithm until the flow of each pipeline stabilizes within ±5% of the target value, forming a stable flow sequence for independent control of a single pipeline. The pressure balance control module uses a pressure transmitter array to monitor the pressure of material pipelines and steam pipelines, filters out noise using a Kalman filter algorithm, and calculates the pressure safety threshold for steam / compressed air pipelines. When the pressure rise rate exceeds the preset alarm threshold, the safety pressure relief device is automatically activated. During normal fluctuations, the opening is adjusted by the pressure regulating valve group, and the pressure deviation is corrected by combining a PID algorithm. The mixing process control module pumps raw materials into the reactor in sequence. After each batch of materials is fed, the frequency conversion control system of the stirring motor is started immediately. Initially, low-speed stirring is used to avoid splashing, and later it is switched to high-speed homogenization. The stirring resistance data is collected in real time by the torque sensor, and the standard deviation of torque fluctuation is calculated by the sliding window algorithm. When the data of three consecutive windows is less than the stable threshold and the preset stirring time is reached, the mixing is judged to be up to standard and a completion signal is generated. The quality assessment and closed-loop control module collects material property parameters through online viscometers and densitometers, uses Kalman filtering algorithm to filter out noise and evaluate indicators, triggers process adjustment instructions when parameters are abnormal, and builds a quality prediction model based on historical data and support vector machine, and optimizes parameters through particle swarm optimization algorithm.

Images