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

Abstract

The invention discloses a mixed emulsion explosive one-key production control method and system, and relates to the field of automatic and intelligent control. By means of automatic and intelligent control means, the problems of low efficiency, high cost, quality fluctuation, process uncertainty and the like in traditional mixed emulsion explosive production are solved, accurate feeding of raw materials is achieved through a quality sensor array and a PID control algorithm, and the production efficiency is improved. The stability of production parameters is ensured through multi-sensor data fusion and an advanced control algorithm, so that the consistency of product quality is improved; meanwhile, a feedback control loop and a continuous learning mechanism are established, closed-loop control in the production process is achieved, technological parameters are optimized, the production stability and reliability are ensured, the production efficiency and the product quality are remarkably improved, and the labor cost is reduced.

Description

Technical Field

[0001] The present invention relates to the field of automation and intelligent control, and in particular to a one-button production control method and system for mixed emulsion explosives. Background Art

[0002] As a core material for modern industrial blasting, mixed emulsion explosives play an irreplaceable role in mining, infrastructure construction, civil engineering, and other fields. With the acceleration of industrialization and the continuous improvement of production safety requirements, higher standards are being set for the precise control and automation level of the mixed emulsion explosive production process. Traditional mixed emulsion explosive production methods rely primarily on manual operation and semi-automated equipment, resulting in low production efficiency, high labor costs, and large fluctuations in product quality. Existing automation solutions often only achieve automatic control of local links, lacking unified management and coordination of the entire production process, making it difficult to meet the needs of modern production.

[0003] In the production process of mixed emulsion explosives, precise control of the raw material ratio directly affects the performance and safety of the product. Liquid ammonium nitrate, diesel, emulsifier and other raw materials need to be mixed in strict proportions. Any slight deviation may lead to significant changes in product quality. When the raw material ratio cannot be precisely automated, key parameters such as temperature, pressure, and flow in the production process will also be difficult to maintain a stable state. Such parameter fluctuations further exacerbate the uncertainty of the production process, making it impossible to form an effective closed-loop control system for the entire production process. Summary of the Invention

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

[0005] The purpose of the present invention can be achieved through the following technical solutions: The present application provides a one-button production control method for mixed emulsion explosives, comprising the following steps: Acquire real-time mass data of liquid ammonium nitrate, diesel, and emulsifiers. Use a mass sensor array to collect weight change information from each raw material storage tank. Calculate the target feed amount based on preset ratio parameters. Based on the logic of independent pipeline delivery of each material, determine the precise feed sequence and independent feed rate control instructions for each raw material. The proportional-integral-differential control algorithm is activated according to the independent feeding control instructions. The flow output of each raw material pipeline is independently adjusted 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 achieved through single-pipeline closed-loop control. Combined with the single-pipeline flow control effect, the fuzzy control algorithm is activated to adjust the power output of the steam indirect heating system and the cooling system, dynamically matching the raw material characteristics and determining the optimal temperature control strategy parameters; A pressure transmitter array is used to monitor the pressure change trends of the reactor, material pipelines, and steam pipelines. Based on the temperature control parameters and pressure changes, the system pressure balance point is calculated, and the pressure of the auxiliary pipelines is maintained stable through the pressure regulating valve group and safety pressure relief device. The raw materials are pumped into the reactor through independent pipelines in order. After each batch of materials is added, the mixing motor frequency conversion control system is started, and the stirring speed and time are adjusted according to the mixing progress of the raw materials. A torque sensor is used to monitor the change in stirring resistance. When the resistance curve tends to be stable, the mixing process is determined to be complete and a mixing process completion signal is generated. The physical properties of the mixed materials are collected through online viscometers and densitometers. The Kalman filter algorithm is activated based on the mixing process completion signal and physical property parameter data to filter out noise and evaluate the status of the measurement data, automatically generating product quality assessment results.

[0006] Furthermore, the precise feeding sequence and independent feeding rate control instructions for each raw material are determined, specifically including: Obtain real-time weight data for liquid ammonium nitrate storage tanks, diesel storage tanks, and emulsifier storage tanks to obtain a stable tank mass change sequence; 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. The material demand within the future time window is calculated. When the remaining available time of the tank falls below the preset safety threshold, a refill signal is automatically triggered, the material replenishment process is started, and the tank refill status indicator is obtained. Based on the preset mass ratio parameters of liquid ammonium nitrate, diesel, and emulsifier, combined with the current production batch target output, the precise feed mass requirements of each raw material are calculated. Then, using the current quality status of the storage tank and the standard feed formula data, the actual feed amount of each raw material is determined through material balance calculations to obtain a feed execution plan. According to the feeding execution plan and the physical properties of each raw material, the PID control algorithm is used to calculate the optimal feeding rate, and the feeding start time and feeding duration are determined at the same time to obtain detailed feeding timing control parameters; The discharge valves and metering pump systems of each storage tank are driven by the feeding timing control parameters, and the changes in mass flow during the feeding process are monitored in real time to obtain an accurate raw material ratio mixture.

[0007] Furthermore, stable single material flow precision control is achieved, specifically including: Obtain the feeding control instruction, determine the independent target flow value of each raw material pipeline by analyzing the instruction data, then initialize the proportional integral differential control algorithm, calculate the opening of the solenoid valve group and the initial speed of the variable frequency pump station, and determine the flow regulation plan; The flow regulation scheme is implemented through a solenoid valve group and a variable frequency pump station. A Coriolis mass flow meter is used 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 exceeds the preset threshold, the proportional integral differential control algorithm is used to recalculate the pump station speed adjustment amount to obtain the 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. The actual flow data after adjustment is continuously monitored through the Coriolis mass flow meter. If the deviation still exceeds the preset threshold, the proportional integral differential control algorithm is iteratively executed to determine the final stable ratio flow rate. 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 through time series analysis to obtain the flow rate prediction model.

[0008] Furthermore, the optimal temperature control strategy parameters are determined, including: Obtain feeding control instructions, determine the independent target flow value of each raw material pipeline by analyzing the instruction data, initialize the proportional integral differential control algorithm, calculate the opening of the solenoid valve group and the initial parameters of the variable frequency pump station, and determine the single pipeline flow regulation plan; A single-pipeline flow control scheme is implemented through a solenoid valve group and a variable-frequency pump station. A Coriolis mass flowmeter is used to collect real-time flow data from each raw material pipeline. When the deviation between the actual flow value and the target flow value of the corresponding pipeline exceeds a preset threshold, the proportional-integral-differential control algorithm is used to recalculate the control parameters and update the solenoid valve group opening and pump station output power. 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 rate of each pipeline is stabilized within ±5% of the target value, forming a stable flow sequence with independent control of each pipeline.

[0009] Furthermore, the pressure in the auxiliary pipeline is maintained stable through the pressure regulating valve group and the safety pressure relief device, specifically including: A pressure transmitter array is used to obtain real-time pressure data from the reactor, material pipeline, and steam pipeline. The Kalman filter algorithm is used to filter out noise and obtain a standardized pressure data set. Calculate the pressure safety thresholds of auxiliary pipelines such as steam and compressed air based on standardized pressure data sets and temperature control parameters, and set the target pressure control range; Real-time analysis of pressure change trends. When the steam / compressed air pipeline pressure rise rate exceeds the preset alarm threshold, a pressure relief control signal is generated to drive the safety pressure relief device to open. When the pressure is within the normal fluctuation range, a pressure regulation control signal is generated to adjust the opening of the pressure regulating valve group, and pressure closed-loop control is achieved through valve position feedback. Based on 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; 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.

[0010] Furthermore, determining a mixing process completion signal specifically includes: Obtain real-time monitoring data from the pressure sensor and raw material feed ratio data, obtain the current mixing progress status value through data fusion processing, and then use the PID control algorithm to calculate the inverter output frequency parameter based on the mixing progress status value and the preset process parameter table to obtain the target speed value of the stirring motor; The stirring motor speed is adjusted to the target speed value through the frequency conversion control system, and the torque sensor data acquisition module is started synchronously to obtain the torque change data sequence during the stirring process. The sliding window method is then used to process the torque change data sequence in real time, and the torque fluctuation variance value within the preset time window is calculated to 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 whether the mixing uniformity meets the standard; According to the mixing uniformity compliance status result, when the judgment result is that the standard is met, a mixing process completion signal is generated and the stirring motor is stopped. When the judgment result is that the standard is not met, the stirring speed is adjusted to continue the mixing process. The pressure parameter change curve, torque fluctuation data and final uniformity evaluation results of the mixing process are saved through the data recording module to form a process parameter optimization database.

[0011] Furthermore, the product quality assessment results are generated, including: The viscosity and density values ​​of the mixed material are collected synchronously by an online viscometer and a 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 collection 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 transfer matrix and the observation matrix. The estimated values ​​of the physical property parameters are then compared with the preset standard range. When the viscosity or density value deviates from the upper and lower limits of the standard range, it is marked as an abnormal state and the need for process adjustment is determined. The process parameter adjustment module is triggered by abnormal status marking. The adjustment range is calculated based on the degree of deviation, and a process adjustment instruction containing the temperature adjustment amount and stirring speed correction value is generated. A weighted scoring algorithm is then used to comprehensively evaluate the adjusted physical parameters. The quality assessment score is calculated based on the compliance of the viscosity and density values ​​to obtain the product quality assessment result. Establish product batch files based on the quality assessment results, record the trajectory of changes in physical parameters and process adjustment history, and form a quality traceability database.

[0012] Furthermore, after obtaining the product quality assessment results, it also includes: establishing a feedback control loop based on the product quality assessment results, calculating the process parameter optimization plan through the historical database and real-time monitoring data, outputting a qualified product signal when the quality indicators are tested qualified three times in a row, and retrospectively adjusting the raw material ratio and process parameters if the quality indicators are detected to be abnormal, thus forming a complete closed-loop control system operation state.

[0013] Furthermore, a feedback control loop is established based on the product quality assessment results, and a process parameter optimization plan is calculated using the historical database and real-time monitoring data, specifically including: Obtain the process parameter records and quality indicator data in the historical database to obtain the historical process data set. Use the support vector machine algorithm to train the historical process data set, establish a mapping relationship model between process parameters and quality indicators, and determine the influence weight of each process parameter on the quality indicator; The real-time monitoring data of the current production process is obtained through the sensor network to obtain the real-time process state parameter matrix. Then, the trained mapping relationship model is input based on the real-time process state parameter matrix to calculate the predicted quality index value and obtain the quality prediction result. When the quality prediction result exceeds the preset qualified threshold three times in a row, a qualified product signal is automatically output and the current process parameter setting continues. When the quality prediction result is lower than the qualified threshold, the parameter adjustment mechanism is triggered; The particle swarm optimization algorithm is used to optimize abnormal process parameters. With the maximization of quality indicators as the objective function, the optimal raw material ratio and process parameter combination are searched within the constraints to determine the parameter adjustment plan. The control instructions of 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 closed-loop control system operation mechanism with continuous learning.

[0014] The present application provides a one-key production control system for mixed emulsion explosives, which is used to implement a one-key production control method for mixed emulsion explosives, including: The raw material feeding control module uses a mass sensor array to collect real-time weight data from liquid ammonium nitrate, diesel, and emulsifier storage tanks. It calculates the feed amount for each raw material based on preset ratios and production targets, uses a linear regression algorithm to predict material consumption, triggers an automatic refill mechanism, and independently adjusts the feed rate of each raw material pipeline through a PID control algorithm, driving valves and metering pumps for precise feeding. The dynamic flow adjustment module, after receiving the feeding control command, independently adjusts the flow of each raw material pipeline through the solenoid valve group and the variable frequency pump station. The actual flow is monitored in real time using the Coriolis mass flow meter. Based on the PID control algorithm, the flow deviation is dynamically corrected. Stable proportion flow control is achieved through iterative adjustment, and a flow prediction model is established to predict fluctuation trends. The intelligent temperature control module collects temperature distribution data in the reactor through a temperature sensor network and calculates the temperature gradient change rate. When the gradient is abnormal, it activates the fuzzy control algorithm to automatically adjust the power output of the steam indirect heating system and the cooling system, dynamically matching the raw material characteristics and optimizing the temperature distribution. The pressure balance control module uses a pressure transmitter array to monitor the pressure of material and steam pipelines, filters out noise using a Kalman filter algorithm, and calculates the pressure safety threshold for steam / compressed air pipelines. When the rate of pressure rise exceeds the preset alarm threshold, the safety pressure relief device automatically activates. During normal fluctuations, the pressure regulating valve group adjusts the opening and uses a PID algorithm to correct pressure deviations. The mixing process control module pumps raw materials into the reactor in sequence. After each batch of materials is added, the mixing motor variable frequency control system is immediately activated, initially using low-speed stirring to avoid splashing, and later switching to high-speed homogenization. A torque sensor collects stirring resistance data in real time, and a sliding window algorithm is used to calculate the standard deviation of torque fluctuations. When three consecutive window data are less than the stability threshold and the preset stirring time is reached, the mixing is determined to have met the requirements and a completion signal is generated. The quality assessment and closed-loop control module collects material physical properties through online viscometers and densitometers, uses the Kalman filter 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 machines, and optimizes parameters through the particle swarm optimization algorithm.

[0015] The beneficial effects of the present invention are: Through automated and intelligent control methods, the entire production process of mixed emulsion explosives is automated. A mass sensor array monitors the weight changes of the raw material storage tanks in real time. Combined with preset mixing parameters and target output, the feed amount and timing of each raw material are accurately calculated. A PID control algorithm is used to optimize the feed rate to ensure the accuracy of the raw material ratio. This process not only solves the problems of low production efficiency and high labor costs caused by reliance on manual operations in traditional production methods, but also significantly improves production efficiency, reduces manual intervention, and lowers labor costs. The present invention achieves real-time monitoring and dynamic adjustment of key parameters in the production process through multi-sensor data fusion and advanced control algorithms. Through the temperature sensor network and fuzzy control algorithm, the temperature distribution in the reactor is precisely controlled to ensure temperature uniformity and stability. At the same time, through the pressure transmitter array and PID control algorithm, the system pressure is dynamically maintained in a stable state, effectively solving the problem of unstable product quality caused by parameter fluctuations in traditional production methods, and improving the consistency and stability of product quality. By establishing a feedback control loop and a continuous learning mechanism, closed-loop control of the production process is achieved. The physical properties of the mixed materials are collected in real time through online viscometers and densitometers. The Kalman filter algorithm is used to filter out noise and estimate the state of the data to generate product quality assessment results. The particle swarm optimization algorithm is then used to search for the optimal raw material ratio and process parameter combination, and the control instructions of the production equipment are updated. This process not only solves the problem of production process uncertainty caused by the lack of unified management and coordination in traditional production methods, but also optimizes the process parameters through a continuous learning mechanism, forming a complete closed-loop control system to ensure the stability and reliability of the production process. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] For better understanding and implementation, the technical solution of the present application is described in detail below with reference to the accompanying drawings.

[0017] Figure 1 A schematic flow chart of the one-button production control method for mixed emulsion explosives provided in Example 1 of the present application; Figure 2 A schematic flow chart of the one-button production control method for mixed emulsion explosives provided in Example 1 of the present application for determining the precise feeding sequence of each raw material and independent feeding rate control instructions; Figure 3 A schematic diagram of a process for obtaining product quality assessment results using the one-key production control method for mixed emulsion explosives provided in Example 1 of the present application; Figure 4 This is a schematic structural diagram of the one-button production control system for mixed emulsion explosives provided in Example 2 of the present application. DETAILED DESCRIPTION

[0018] To further illustrate the technical means and effectiveness of the present invention in achieving its intended purpose, exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. In the following description, when referring to the drawings, identical numerals in different figures represent identical or similar elements, unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all possible embodiments consistent with the present application. Rather, they are merely examples of methods and systems consistent with certain aspects of the present application, as detailed in the appended claims.

[0019] The terms used in this application are for the purpose of describing specific embodiments only and are not intended to limit this application. As used in this application and the appended claims, the singular forms "a," "an," "the," and "the" are intended to include the plural forms, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.

[0020] The following describes in detail the specific implementation methods, features and effects of the present invention in conjunction with the accompanying drawings and preferred embodiments.

[0021] Example 1

[0022] See also Figure 1-Figure 3 This embodiment provides a one-key production control method for mixed emulsion explosives, comprising the following steps: S1. Acquire real-time mass data of liquid ammonium nitrate, diesel, and emulsifier. Use a mass sensor array to collect weight change information from each raw material storage tank. Calculate the target feed amount based on preset mixing parameters. Determine the precise feed sequence and independent feed rate control instructions for each raw material based on independent pipeline delivery logic for each material. Furthermore, the precise feeding sequence and independent feeding rate control instructions for each raw material are determined, specifically including: S11. Acquire real-time weight data of the liquid ammonium nitrate storage tank, the diesel storage tank, and the emulsifier storage tank collected by the mass sensor array, and filter out sensor noise interference through a data preprocessing module to obtain a stable tank mass change sequence; S12. 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. The material demand within the future time window is calculated to obtain the remaining available time of each tank. When the remaining available time of a tank falls below a preset safety threshold, a refill signal for the corresponding tank is automatically triggered, and the material replenishment process is initiated through the refill control system, and a tank refill status indicator is obtained. S13. Based on the preset mass ratio parameters of liquid ammonium nitrate, diesel, and emulsifier, combined with the current production batch target output, the precise feeding quality requirements of each raw material are calculated to obtain standard feeding formula data. Then, using the current quality status of the storage tank and the standard feeding formula data, the actual feed amount of each raw material is determined through material balance calculation. When the actual feed amount meets the formula requirements, a feeding permission mark is generated, and a feeding execution plan is obtained; S14. Based on the feeding execution plan and the physical property parameters of each raw material, a PID control algorithm is used to calculate the optimal feeding rates of liquid ammonium nitrate, diesel, and emulsifier, and the feeding start time and feeding duration are determined at the same time to obtain detailed feeding timing control parameters; wherein the feeding rate of each raw material pipeline is independently controlled, and a single pipeline only transports one raw material; S15. The discharge valves and metering pump systems of each storage tank are driven by the feeding timing control parameters. The raw materials are pumped into the reactor through independent pipelines in the order of "liquid ammonium nitrate → diesel → emulsifier". The changes in mass flow during the feeding process are monitored in real time to obtain an accurate raw material ratio mixture.

[0023] Specifically, through precise monitoring and intelligent control, accurate feeding of raw materials in the production of mixed emulsion explosives is achieved, which ensures the continuity and stability of production, improves product quality and safety, and at the same time reduces production costs and manual intervention, thereby improving production efficiency.

[0024] S2. Activate the proportional-integral-derivative (PID) control algorithm based on independent feed control instructions, and independently adjust the flow output of each raw material pipeline through the solenoid valve group and variable frequency pump station (for example, the liquid ammonium nitrate pipeline independently adjusts the flow rate, and the same applies to the diesel and emulsifier pipelines). Use a Coriolis mass flowmeter to monitor the actual feed flow data of each pipeline in real time. Through single-pipeline closed-loop control, stable single-material flow accuracy control is achieved, avoiding the coordinated proportioning of multiple material pipelines. Furthermore, stable single material flow precision control is achieved, specifically including: Obtain the feeding control instruction, determine the independent target flow value of each raw material pipeline by analyzing the instruction data (not involving the proportion ratio), then initialize the proportional integral differential control algorithm, calculate the opening of the solenoid valve group and the initial speed of the variable frequency pump station, and determine the flow regulation plan; The flow regulation scheme is implemented through the solenoid valve group and variable frequency pump station. The Coriolis mass flowmeter is used to collect the actual flow data of each raw material pipeline in real time to obtain the actual flow value. When the deviation between the actual flow value and the target flow value exceeds the preset threshold, the proportional integral differential control algorithm is used to recalculate the pump station speed adjustment amount to obtain the new speed control parameters, realizing closed-loop control of the single pipeline flow. By adjusting the operating frequency of the variable frequency pump station and updating the flow output of the raw material pipeline, the adjusted actual flow data is obtained. The adjusted actual flow data is then continuously monitored using a Coriolis mass flow meter. If the deviation still exceeds the preset threshold, the proportional integral differential control algorithm is iteratively executed to determine the final stable proportion flow rate. 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 through time series analysis to obtain the flow rate prediction model.

[0025] Specifically, a proportional-integral-derivative (PID) control algorithm, combined with a solenoid valve assembly and variable-frequency pumping station, achieves precise regulation and stable control of the flow rates in each raw material pipeline. Real-time monitoring by Coriolis mass flowmeters ensures high accuracy and reliability of flow data. By iteratively adjusting the pumping station speed, the system can quickly respond and correct flow deviations, ultimately achieving stable raw material ratio flow control. Furthermore, time series analysis, which predicts future flow fluctuations, further enhances the system's predictive capabilities and stability, ensuring production continuity and consistent product quality.

[0026] S3. Integrating the single-pipeline flow control effect, the fuzzy control algorithm is activated to adjust the power output of the steam indirect heating system (steam does not directly contact the material, but heats up through heat conduction in the jacket or coil) and the cooling system, dynamically matching the raw material characteristics (such as the crystallization temperature of liquid ammonium nitrate) and determining the optimal temperature control strategy parameters (such as heating power and cooling start and stop thresholds). Furthermore, the optimal temperature control strategy parameters are determined, including: Obtain feeding control instructions, determine the independent target flow value of each raw material pipeline by parsing the instruction data (not involving the proportion ratio), initialize the proportional integral differential (PID) control algorithm, calculate the opening of the solenoid valve group and the initial parameters of the variable frequency pump station, and determine the single pipeline flow regulation plan; A single-pipeline flow control solution is implemented through a solenoid valve group and a variable-frequency pump station. A Coriolis mass flowmeter collects real-time flow data from each raw material pipeline. When the deviation between the actual flow value and the target flow value for the corresponding pipeline exceeds a preset threshold, the PID control algorithm recalculates the control parameters, updates the solenoid valve group opening and the pump station output power, and achieves closed-loop control of the single-pipeline flow. The actual flow data after adjustment is continuously monitored. If the deviation still exceeds the threshold, the PID algorithm is iteratively executed until the flow of each pipeline is stabilized within the range of ±5% of the target value, forming a stable flow sequence with independent control of each pipeline.

[0027] Specifically, the temperature distribution in the reactor is monitored in real time through a temperature sensor network, and the power output of the heating and cooling systems is dynamically adjusted using a fuzzy control algorithm. This can effectively respond to changes in temperature gradients and ensure the uniformity and stability of temperature distribution. When the temperature gradient change rate exceeds the safety threshold, the heating and cooling parameters are automatically adjusted. Through iterative optimization, the optimality of the temperature control strategy is ensured, thereby improving the safety of the production process and the consistency of product quality.

[0028] S4. Use a pressure transmitter array to monitor pressure trends in the reactor (normal pressure environment, no tank pressure control required), material pipelines, and steam pipelines. Calculate the system pressure equilibrium point (such as the steam pipeline pressure safety threshold) based on temperature control parameters and pressure changes. Maintain pressure stability in auxiliary pipelines such as steam and compressed air through a pressure regulating valve group and safety pressure relief device to ensure safe operation of the reactor at normal pressure. Furthermore, the pressure of auxiliary pipelines such as steam and compressed air is maintained stable through pressure regulating valve groups and safety pressure relief devices, including: A pressure transmitter array is used to obtain real-time pressure data from the reactor (normal pressure environment, no pressure control requirements), material pipelines, and steam pipelines. The Kalman filter algorithm is used to filter out noise and obtain a standardized pressure data set. Calculate the pressure safety threshold (i.e., system pressure balance point) of auxiliary pipelines such as steam and compressed air based on standardized pressure data sets and temperature control parameters, and set the target pressure control range; Real-time analysis of pressure change trends. When the steam / compressed air pipeline pressure rise rate exceeds the preset alarm threshold, a pressure relief control signal is generated to drive the safety pressure relief device to open. When the pressure is within the normal fluctuation range, a pressure regulation control signal is generated to adjust the opening of the pressure regulating valve group, and pressure closed-loop control is achieved through valve position feedback. Based on the pressure response data (such as the pressure drop rate after pressure relief and the pressure stability 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 within the target range (such as steam pressure ≤ 0.3MPa); 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.

[0029] Specifically, real-time pressure data is collected through a pressure transmitter array and a Kalman filter algorithm is used to filter out noise. Combined with temperature control parameters, the pressure safety threshold is accurately calculated and the target pressure control range is set. The system analyzes pressure trends in real time, quickly activating the safety pressure relief device when the alarm threshold is exceeded. During normal fluctuations, the pressure regulating valve group opening is adjusted to achieve closed-loop control. Parameters are dynamically adjusted based on the pressure response data to ensure that the auxiliary pipeline pressure remains stable within the target range and achieve dynamic balance. This process effectively prevents system overpressure, ensures production safety, and optimizes the production process, improving product quality stability, and reducing safety risks.

[0030] S5. Liquid ammonium nitrate → diesel → emulsifier are pumped into the reactor in the order of "liquid ammonium nitrate → diesel → emulsifier" through independent pipelines. After each batch of materials is added, the mixing motor variable frequency control system is activated, and the stirring speed and time are adjusted according to the mixing progress of the raw materials (for example, initially stirring at a low speed to avoid splashing, and then stirring at a high speed for homogenization in the later stage). A torque sensor is used to monitor the change in stirring resistance. When the resistance curve tends to be stable, the mixing process is determined to be complete, and a mixing process completion signal is generated; Furthermore, determining a mixing process completion signal specifically includes: Obtain real-time monitoring data from the pressure sensor and raw material feed ratio data, obtain the current mixing progress status value through data fusion processing, and then use the PID control algorithm to calculate the inverter output frequency parameter based on the mixing progress status value and the preset process parameter table to obtain the target speed value of the stirring motor; The stirring motor speed is adjusted to the target speed value through the frequency conversion control system, and the torque sensor data acquisition module is started synchronously to obtain the torque change data sequence during the stirring process. The sliding window method is then used to process the torque change data sequence in real time, and the torque fluctuation variance value within the preset time window is calculated to 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 whether the mixing uniformity meets the standard; According to the mixing uniformity compliance status result, when the judgment result is that the standard is met, a mixing process completion signal is generated and the stirring motor is stopped. When the judgment result is that the standard is not met, the stirring speed is adjusted to continue the mixing process. The pressure parameter change curve, torque fluctuation data and final uniformity evaluation results of the mixing process are saved through the data recording module to form a process parameter optimization database.

[0031] Specifically, the coordinated operation of the mixing motor's variable frequency control system and torque sensor enables precise control of the mixing process and real-time monitoring of mixing uniformity. Based on the dynamic equilibrium state of pressure parameters and the progress of raw material mixing, the mixing speed and time are dynamically adjusted to ensure efficient and uniform mixing. A sliding window method and a machine learning algorithm (support vector machine) are used to evaluate the stirring resistance stability index, accurately determining whether mixing uniformity meets the standard and generating a mixing process completion signal accordingly. This process not only improves the level of production automation but also provides data support for the continuous optimization of process parameters through the data recording module, thereby improving the stability and consistency of product quality.

[0032] S6. Collect the physical properties of the mixed material through the online viscometer and density meter, start the Kalman filter algorithm based on the mixing process completion signal and physical property parameter data, filter the noise and evaluate the status of the measurement data, and automatically generate the product quality evaluation results.

[0033] Furthermore, the product quality assessment results are generated, including: S61. Synchronously collect the viscosity and density values ​​of the mixed material using an online viscometer and densitometer to obtain a real-time physical property parameter data set. The physical property parameter data are then arranged in a time series according to a preset data collection frequency. When the data collection interval exceeds a preset time threshold, a data compensation mechanism is triggered to obtain a continuous and complete measurement data sequence. S62. Process the measurement data sequence using a Kalman filter algorithm, establish a mathematical model using a state transition matrix and an observation matrix, obtain estimated values ​​of physical property parameters after noise filtering, and then compare the estimated values ​​of the physical property parameters with the preset standard range. When the viscosity value or density value deviates from the upper or lower limit of the standard range, it is marked as an abnormal state, and the need for process adjustment is determined; S63. Triggering the process parameter adjustment module through the abnormal status flag calculates the adjustment range based on the degree of deviation, generates a process adjustment instruction including the temperature adjustment amount and the stirring speed correction value, and then uses a weighted scoring algorithm to comprehensively evaluate the adjusted physical parameters. Calculate the quality assessment score based on whether the viscosity and density values ​​meet the standards to obtain the product quality assessment result; S64. Establish product batch files based on the quality assessment results, record the trajectory of changes in physical parameters and process adjustment history, and form a quality traceability database.

[0034] Specifically, the physical properties of the mixed materials are collected in real time through online viscometers and densitometers, and the Kalman filter algorithm is used to filter out noise and estimate the state of the data. This can accurately monitor the key indicators of product quality. When the physical properties deviate from the preset standard range, the process adjustment instructions are automatically triggered. By calculating the adjustment range and generating a specific process adjustment plan, it is ensured that the product quality meets the standards. In addition, the adjusted physical properties are comprehensively evaluated through a weighted scoring algorithm, and the quality assessment score is calculated to ultimately form the product quality assessment result. This process not only improves the stability and consistency of product quality, but also provides strong support for the optimization of the production process and quality control by establishing product batch files and quality traceability databases.

[0035] Furthermore, it also includes: the raw material conveying pipeline is equipped with a cleaning and purging system. When a production batch switching signal or a shutdown command is detected, the steam purging program is automatically executed (using the steam pipeline to connect the material pipeline for purging) to remove residual materials in the pipeline; at the same time, the safety interlock is triggered to ensure that the system enters the standby state after the purging is completed.

[0036] Furthermore, after obtaining the product quality assessment results, it also includes: establishing a feedback control loop based on the product quality assessment results, calculating the process parameter optimization plan through the historical database and real-time monitoring data, outputting a qualified product signal when the quality indicators are tested qualified three times in a row, and retrospectively adjusting the raw material ratio and process parameters if the quality indicators are detected to be abnormal, thus forming a complete closed-loop control system operation state.

[0037] Furthermore, a feedback control loop is established based on the product quality assessment results, and a process parameter optimization plan is calculated using the historical database and real-time monitoring data, specifically including: Obtain the process parameter records and quality indicator data in the historical database to obtain the historical process data set. Use the support vector machine algorithm to train the historical process data set, establish a mapping relationship model between process parameters and quality indicators, and determine the influence weight of each process parameter on the quality indicator; Real-time monitoring data from the current production process, including temperature, pressure, flow rate, and raw material ratio information, is acquired through a sensor network to obtain a real-time process state parameter matrix. This matrix is ​​then input into a trained mapping relationship model to calculate the predicted quality index value Q = f(T, P, F, R), where T represents the temperature parameter, P represents the pressure parameter, F represents the flow parameter, and R represents the raw material ratio parameter, to obtain the quality prediction result. When the quality prediction result exceeds the preset qualified threshold three times in a row, the system automatically outputs a qualified product signal and continues the current process parameter setting. When the quality prediction result is lower than the qualified threshold, the parameter adjustment mechanism is triggered; The particle swarm optimization algorithm is used to optimize abnormal process parameters. With the maximization of quality indicators as the objective function, the optimal raw material ratio and process parameter combination are searched within the constraints to determine the parameter adjustment plan. The control instructions of 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 closed-loop control system operation mechanism with continuous learning.

[0038] Specifically, through feedback control loops and advanced algorithms, process parameters are dynamically optimized according to product quality assessment results. Historical data and real-time monitoring are used to establish a mapping relationship model, predict quality indicators and automatically adjust parameters to form a closed-loop control. This not only improves the stability and consistency of product quality, but also optimizes process parameters through a continuous learning mechanism, thereby improving production efficiency and intelligence.

[0039] Example 2

[0040] See also Figure 4 This embodiment provides a one-key production control system for mixed emulsion explosives, which is used to implement a one-key production control method for mixed emulsion explosives, including: The raw material feeding control module uses a mass sensor array to collect real-time weight data from liquid ammonium nitrate, diesel, and emulsifier storage tanks. It calculates the feed amount of each raw material based on the preset ratio and production target, uses a linear regression algorithm to predict material consumption, triggers the automatic feeding mechanism, and independently adjusts the feeding rate of each raw material pipeline through a PID control algorithm. It drives valves and metering pumps for precise feeding and ensures the accuracy of the raw material ratio. The dynamic flow adjustment module, upon receiving the feed control command, independently adjusts the flow of each raw material pipeline (e.g., liquid ammonium nitrate, diesel, and emulsifier pipelines are individually controlled) through the solenoid valve group and variable frequency pump station. It uses a Coriolis mass flowmeter to monitor the actual flow in real time and dynamically corrects flow deviations based on the PID control algorithm. It achieves stable proportioning flow control through iterative adjustment and establishes a flow prediction model to anticipate fluctuation trends. The intelligent temperature control module collects temperature distribution data within the reactor through a temperature sensor network and calculates the rate of change of the temperature gradient. When the gradient is abnormal, it activates a fuzzy control algorithm to automatically adjust the power output of the steam indirect heating system (steam conducts heat through the jacket / coil) and the cooling system, dynamically matching the raw material characteristics (such as the crystallization temperature of liquid ammonium nitrate) to optimize the temperature distribution and ensure uniform and stable reaction temperature. The pressure balance control module uses a pressure transmitter array to monitor the pressure of material and steam pipelines (the reactor is at atmospheric pressure, so there is no need for pressure control). It uses a Kalman filter algorithm to filter out noise and calculate the pressure safety threshold (system pressure balance point) for the steam / compressed air pipeline. When the rate of pressure rise exceeds the preset alarm threshold, the safety pressure relief device automatically activates. During normal fluctuations, the pressure regulating valve group adjusts the opening, and combined with the PID algorithm, corrects pressure deviations to ensure that the auxiliary pipeline pressure remains stable within the target range (e.g., steam pressure ≤ 0.3 MPa). The mixing process control module pumps liquid ammonium nitrate into the reactor in the order of "liquid ammonium nitrate → diesel → emulsifier". The variable frequency control system for the stirring motor is activated immediately after each batch of materials is added. Initially, low-speed stirring (e.g., 50 rpm) is used to avoid splashing, and later it is switched to high-speed homogenization (e.g., 150 rpm). A torque sensor collects stirring resistance data in real time, and a sliding window algorithm is used to calculate the standard deviation of torque fluctuations. When three consecutive window data values ​​are less than a stability threshold (e.g., 0.5 N·m) and the preset stirring time (e.g., 15 minutes) is reached, the mixing is determined to have met the requirements and a completion signal is generated. If the requirements are not met, the stirring time is automatically extended or the speed is adjusted. Pressure data and support vector machine evaluation logic are eliminated, and the material is transported through independent pipelines based solely on torque stability and time parameters. The quality assessment and closed-loop control module collects material properties using an online viscometer and density meter, filters out noise, and evaluates performance using a Kalman filter. When parameters are abnormal, process adjustments (such as temperature and stirring speed corrections) are triggered. A quality prediction model is constructed based on historical data and a support vector machine. Particle swarm optimization is used to optimize parameters, forming a closed-loop control system called "detection-adjustment-learning" to ensure stable product quality.

[0041] The above description is merely a preferred embodiment of the present invention and does not constitute any form of limitation to the present invention. Although the present invention has been disclosed as above in terms of a preferred embodiment, it is not intended to limit the present invention. Any person skilled in the art can, without departing from the scope of the technical solution of the present invention, make some changes or modifications to equivalent embodiments using the technical contents disclosed above. However, any brief modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solution of the present invention are still within the scope of the technical solution of the present invention.

Claims

1. A one-button production control method for mixed emulsion explosives, characterized by: The steps include: Acquire real-time mass data of liquid ammonium nitrate, diesel, and emulsifiers. Use a mass sensor array to collect weight change information from each raw material storage tank. Calculate the target feed amount based on preset ratio parameters. Transport each material through independent pipelines, determine the precise feed sequence and independent feed rate control instructions for each raw material. The proportional-integral-differential control algorithm is activated according to the independent feeding control instructions. The flow output of each raw material pipeline is independently adjusted 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 achieved through single-pipeline closed-loop control. Combined with the single-pipeline flow control effect, the fuzzy control algorithm is activated to adjust the power output of the steam indirect heating system and the cooling system, dynamically matching the raw material characteristics and determining the optimal temperature control strategy parameters; A pressure transmitter array is used to monitor the pressure change trends of the reactor, material pipelines, and steam pipelines. Based on the temperature control parameters and pressure changes, the system pressure balance point is calculated, and the pressure of the auxiliary pipelines is maintained stable through the pressure regulating valve group and safety pressure relief device. The raw materials are pumped into the reactor through independent pipelines in order. After each batch of materials is added, the mixing motor frequency conversion control system is started and the mixing speed and time are adjusted according to the mixing progress of the raw materials. A torque sensor is used to monitor the change in stirring resistance. When the resistance curve tends to be stable, the mixing process is determined to be completed and a mixing process completion signal is determined. The physical properties of the mixed materials are collected through online viscometers and densitometers. The Kalman filter algorithm is activated based on the mixing process completion signal and physical property parameter data. The measurement data is subjected to noise filtering and status evaluation to obtain product quality evaluation results.

2. The one-button production control method for mixed emulsion explosives according to claim 1, characterized in that: Determine the precise feeding sequence and independent feeding rate control instructions for each raw material, including: Obtain real-time weight data for liquid ammonium nitrate storage tanks, diesel storage tanks, and emulsifier storage tanks to obtain a stable tank mass change sequence; 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. The material demand within the future time window is calculated. When the remaining available time of the tank falls below the preset safety threshold, a refill signal is automatically triggered, the material replenishment process is started, and the tank refill status indicator is obtained. Based on the preset mass ratio parameters of liquid ammonium nitrate, diesel, and emulsifier, combined with the current production batch target output, the precise feed mass requirements of each raw material are calculated. Then, using the current quality status of the storage tank and the standard feed formula data, the actual feed amount of each raw material is determined through material balance calculations to obtain a feed execution plan. According to the feeding execution plan and the physical properties of each raw material, the PID control algorithm is used to calculate the optimal feeding rate, and the feeding start time and feeding duration are determined at the same time to obtain detailed feeding timing control parameters; The discharge valves and metering pump systems of each storage tank are driven by the feeding timing control parameters, and the changes in mass flow during the feeding process are monitored in real time to obtain an accurate raw material ratio mixture.

3. The one-button production control method for mixed emulsion explosives according to claim 1, characterized in that: Obtain stable single material flow precision control, including: Obtain the feeding control instruction, determine the independent target flow value of each raw material pipeline by analyzing the instruction data, then initialize the proportional integral differential control algorithm, calculate the opening of the solenoid valve group and the initial speed of the variable frequency pump station, and determine the flow regulation plan; The flow regulation scheme is implemented through the solenoid valve group and the variable frequency pump station. The actual flow data is collected in real time using a Coriolis mass flowmeter. When the deviation between the actual flow value and the target flow value exceeds the preset threshold, the proportional integral differential control algorithm is used to recalculate the pump station speed adjustment amount to obtain the 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. The actual flow data after adjustment is continuously monitored through the Coriolis mass flow meter. If the deviation still exceeds the preset threshold, the proportional integral differential control algorithm is iteratively executed to determine the final stable ratio flow rate. 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 through time series analysis to obtain the flow rate prediction model.

4. The one-button production control method for mixed emulsion explosives according to claim 1, characterized in that: Determine the optimal temperature control strategy parameters, including: Obtain feeding control instructions, determine the independent target flow value of each raw material pipeline by analyzing the instruction data, initialize the proportional integral differential control algorithm, calculate the opening of the solenoid valve group and the initial parameters of the variable frequency pump station, and determine the single pipeline flow regulation plan; A single-pipeline flow control scheme is implemented through a solenoid valve group and a variable-frequency pump station. A Coriolis mass flowmeter is used to collect real-time flow data from each raw material pipeline. When the deviation between the actual flow value and the target flow value of the corresponding pipeline exceeds a preset threshold, the proportional-integral-differential control algorithm is used to recalculate the control parameters and update the solenoid valve group opening and pump station output power. 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 rate of each pipeline is stabilized within ±5% of the target value, forming a stable flow sequence with independent control of each pipeline.

5. The one-button production control method for mixed emulsion explosives according to claim 1, characterized in that: Maintaining stable pressure in the auxiliary pipelines through pressure regulating valves and safety pressure relief devices includes: A pressure transmitter array is used to obtain real-time pressure data from the reactor, material pipeline, and steam pipeline. The Kalman filter algorithm is used to filter out noise and obtain a standardized pressure data set. Calculate the pressure safety threshold of the auxiliary pipeline based on the standardized pressure data set and temperature control parameters, and set the target pressure control range; Real-time analysis of pressure change trends. When the steam / compressed air pipeline pressure rise rate exceeds the preset alarm threshold, a pressure relief control signal is generated to drive the safety pressure relief device to open. When the pressure is within the normal fluctuation range, a pressure regulation control signal is generated to adjust the opening of the pressure regulating valve group, and pressure closed-loop control is achieved through valve position feedback. Based on 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; 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.

6. The one-button production control method for mixed emulsion explosives according to claim 1, characterized in that: Determine the mixing process completion signal, including: Obtain real-time monitoring data from the pressure sensor and raw material feed ratio data, obtain the current mixing progress status value through data fusion processing, and then use the PID control algorithm to calculate the inverter output frequency parameter based on the mixing progress status value and the preset process parameter table to obtain the target speed value of the stirring motor; The stirring motor speed is adjusted to the target speed value through the frequency conversion control system, and the torque sensor data acquisition module is started synchronously to obtain the torque change data sequence during the stirring process. The sliding window method is then used to process the torque change data sequence in real time, and the torque fluctuation variance value within the preset time window is calculated to 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 whether the mixing uniformity meets the standard; According to the mixing uniformity compliance status result, when the judgment result is that the standard is met, a mixing process completion signal is generated and the stirring motor is stopped. When the judgment result is that the standard is not met, the stirring speed is adjusted to continue the mixing process. The pressure parameter change curve, torque fluctuation data and final uniformity evaluation results of the mixing process are saved through the data recording module to form a process parameter optimization database.

7. The one-button production control method for mixed emulsion explosives according to claim 1, characterized in that: Get product quality assessment results, including: The viscosity and density values ​​of the mixed material are collected synchronously by an online viscometer and a 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 collection 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 transfer matrix and the observation matrix. The estimated values ​​of the physical property parameters are then compared with the preset standard range. When the viscosity or density value deviates from the upper and lower limits of the standard range, it is marked as an abnormal state and the need for process adjustment is determined. The process parameter adjustment module is triggered by abnormal status marking. The adjustment range is calculated based on the degree of deviation, and a process adjustment instruction containing the temperature adjustment amount and stirring speed correction value is generated. A weighted scoring algorithm is then used to comprehensively evaluate the adjusted physical parameters. The quality assessment score is calculated based on the compliance of the viscosity and density values ​​to obtain the product quality assessment result. Establish product batch files based on the quality assessment results, record the trajectory of changes in physical parameters and process adjustment history, and form a quality traceability database.

8. The one-button production control method for mixed emulsion explosives according to claim 7, characterized in that: After obtaining the product quality assessment results, it also includes: establishing a feedback control loop based on the product quality assessment results, calculating the process parameter optimization plan through the historical database and real-time monitoring data, outputting a qualified product signal when the quality indicators are tested qualified three times in a row, and retrospectively adjusting the raw material ratio and process parameters if the quality indicators are detected to be abnormal, thus forming a complete closed-loop control system operation state.

9. The one-key production control method for mixed emulsion explosives according to claim 8, characterized in that: Establish a feedback control loop based on the product quality assessment results, and calculate the process parameter optimization plan through the historical database and real-time monitoring data, including: Obtain the process parameter records and quality indicator data in the historical database to obtain the historical process data set. Use the support vector machine algorithm to train the historical process data set, establish a mapping relationship model between process parameters and quality indicators, and determine the influence weight of each process parameter on the quality indicator; The real-time monitoring data of the current production process is obtained through the sensor network to obtain the real-time process state parameter matrix. Then, the trained mapping relationship model is input based on the real-time process state parameter matrix to calculate the predicted quality index value and obtain the quality prediction result. When the quality prediction result exceeds the preset qualified threshold three times in a row, a qualified product signal is automatically output and the current process parameter setting continues. When the quality prediction result is lower than the qualified threshold, the parameter adjustment mechanism is triggered; The particle swarm optimization algorithm is used to optimize abnormal process parameters. With the maximization of quality indicators as the objective function, the optimal raw material ratio and process parameter combination are searched within the constraints to determine the parameter adjustment plan. The control instructions of 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 closed-loop control system operation mechanism with continuous learning.

10. A one-touch production control system for mixed emulsion explosives, applied to the one-touch production control method for mixed emulsion explosives according to any one of claims 1 to 9, characterized in that: include: The raw material feeding control module uses a mass sensor array to collect real-time weight data from liquid ammonium nitrate, diesel, and emulsifier storage tanks. It calculates the feed amount for each raw material based on preset ratios and production targets, uses a linear regression algorithm to predict material consumption, triggers an automatic refill mechanism, and independently adjusts the feed rate of each raw material pipeline through a PID control algorithm, driving valves and metering pumps for precise feeding. The dynamic flow adjustment module, after receiving the feeding control command, independently adjusts the flow of each raw material pipeline through the solenoid valve group and the variable frequency pump station. The actual flow is monitored in real time using the Coriolis mass flow meter. Based on the PID control algorithm, the flow deviation is dynamically corrected. Stable proportion flow control is achieved through iterative adjustment, and a flow prediction model is established to predict fluctuation trends. The intelligent temperature control module collects temperature distribution data in the reactor through a temperature sensor network and calculates the temperature gradient change rate. When the gradient is abnormal, it activates the fuzzy control algorithm to automatically adjust the power output of the steam indirect heating system and the cooling system, dynamically matching the raw material characteristics and optimizing the temperature distribution. The pressure balance control module uses a pressure transmitter array to monitor the pressure of material and steam pipelines, filters out noise using a Kalman filter algorithm, and calculates the pressure safety threshold for steam / compressed air pipelines. When the rate of pressure rise exceeds the preset alarm threshold, the safety pressure relief device automatically activates. During normal fluctuations, the pressure regulating valve group adjusts the opening and uses a PID algorithm to correct pressure deviations. The mixing process control module pumps the raw materials into the reactor in sequence. The mixing motor frequency conversion control system is started immediately after each batch of materials is added. The initial stirring speed is low to avoid splashing, and then it is switched to high-speed homogenization in the later stage. The torque sensor collects stirring resistance data in real time, and a sliding window algorithm is used to calculate the standard deviation of torque fluctuations. When three consecutive window data are less than the stability threshold and the preset stirring time is reached, the mixing is judged to have met the standards and a completion signal is generated. The quality assessment and closed-loop control module collects material physical properties through online viscometers and densitometers, uses the Kalman filter 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 machines, and optimizes parameters through the particle swarm optimization algorithm.

Images