High-quality phosphate chemical process automation system

Abstract

The invention relates to the technical field of automation control, in particular to a high-quality phosphate chemical process automation system which comprises a resource demand prediction module, a concentration prediction adjustment module, a temperature real-time control module, a production data analysis module and a deviation correction module. According to the method, through material consumption prediction and concentration adjustment, in combination with temperature and flow control, accurate adjustment can be carried out in time, optimization of production efficiency and quality is guaranteed, errors caused by manual operation or system deviation in the production process are effectively avoided by analyzing deviation data and correcting deviation exceeding an allowable range, and the production quality is improved. The self-adaptive capacity of production is enhanced, product consistency and production stability are optimized, production parameters of all links can be adjusted in real time, it is ensured that the whole process is efficient and stable, resource use is optimized, energy consumption and material waste are reduced, and the production process better meets the requirements of green and sustainable development.

Description

Technical Field

[0001] The present invention relates to the technical field of automation control, and particularly to an automated system for high-quality phosphate chemical processes. Background Art

[0002] The technical field of automation control involves using various control theories and technical means to achieve automatic regulation and control of equipment, machines, systems, or processes. Its core objective is to perform real-time monitoring and adjustment of various physical quantities in the process through automated devices, sensors, actuators, and computer systems, reducing manual intervention and improving production efficiency, accuracy, and stability. This technical field is widely applied in industries such as chemical engineering, manufacturing, energy, and transportation, supporting efficient, precise, and safe industrial production. Common automation control technologies include PID control, fuzzy control, advanced process control, etc.

[0003] Among them, the automated system for high-quality phosphate chemical processes aims to perform intelligent control and adjustment of various links in the phosphate chemical production process. This system realizes real-time monitoring and adjustment of important parameters such as reaction kettles, temperature, pressure, flow rate, and concentration through automation technology, ensuring the efficient and safe operation of chemical reactions. Its main purpose is to improve the accuracy and stability of the production process, reduce human operation errors, improve product quality and output, while reducing energy consumption and material waste. This automated system optimizes production efficiency and resource utilization by integrating modern control technologies, contributing to the sustainable development of the phosphate chemical industry.

[0004] Traditional automated systems rely on traditional control theories such as conventional PID control and fuzzy control. Although they can achieve parameter adjustment, the control methods do not fully consider the dynamic changes of various parameters in the production process and their mutual relationships, and there is insufficient real-time feedback in the production process, resulting in a lag in response to sudden changes during the adjustment process, leading to a decrease in production efficiency or resource waste. At the same time, the deviation detection in traditional systems is relatively basic, making it difficult to accurately identify and adjust subtle changes in the production links, and unable to dynamically adjust the resource allocation of each link, resulting in misoperations or system instability. Traditional systems have problems such as insufficient sensitivity in response, low adjustment accuracy, and non-optimized resource allocation, making it difficult to achieve the best economic and environmental benefits in the production process. Summary of the Invention

[0005] The purpose of the present invention is to solve the disadvantages existing in the prior art, and to propose an automated system for high-quality phosphate chemical processes.

[0006] To achieve the above purpose, the present invention adopts the following technical solution: An automated system for high-quality phosphate chemical processes, the system includes:

[0007] The resource demand prediction module obtains the production records of phosphate chemical industry, extracts the current production targets and raw material quality information, analyzes the raw material consumption trends under different production targets, and calculates the consumption quantity and usage trends of the required materials based on the current production targets and raw material quality, so as to generate material usage prediction information;

[0008] The concentration prediction and adjustment module, based on the material usage prediction information, collects real-time reaction concentration data, analyzes the concentration change trends, predicts future concentration changes, and calculates the adjustment values of the reaction rate and the feeding quantity according to the target concentration and the predicted concentration change trends, so as to obtain concentration adjustment information;

[0009] The temperature real-time control module, based on the concentration adjustment information, collects the temperature data at multiple positions of the reaction kettle in real time, combines the normal reaction data, analyzes the temperature change trends, and selects the corresponding temperature control strategy according to the reaction stage to adjust the heating rate and temperature accuracy, so as to obtain temperature adjustment information;

[0010] The production data analysis module, based on the temperature adjustment information, collects the key production data in the process of phosphate chemical production, monitors the real-time changes of each parameter, and compares them with the set reference values to obtain the deviation degree of each production link, so as to obtain production deviation data.

[0011] The improvement of the present invention is that the material usage prediction information includes the types of raw materials, the predicted usage quantity and usage trends; the concentration adjustment information includes the adjustment quantity of the reaction rate, the adjustment value of the feeding quantity and the concentration change range; the temperature adjustment information includes the heating rate, the temperature accuracy and the temperature control strategy; and the production deviation data includes the temperature deviation value, the pressure deviation value and the flow deviation value.

[0012] The improvement of the present invention is that the resource demand prediction module includes:

[0013] The production data extraction sub-module obtains the production records of phosphate chemical industry, extracts the current production targets and raw material quality information, and combines the material usage data in the normal production mode to obtain a reference data set;

[0014] The raw material consumption analysis sub-module, based on the reference data set, analyzes the raw material consumption trends under multiple production targets, calculates the consumption ratio of raw materials in each stage, and generates raw material consumption trend data;

[0015] The material consumption calculation sub-module, according to the raw material consumption trend data, combines the current production targets and raw material quality data, calculates the consumption quantity and usage trends of the required materials, and generates material usage prediction information.

[0016] The improvement of the present invention is that the concentration prediction and adjustment module includes:

[0017] The concentration data acquisition sub-module obtains the material usage prediction information, and collects the reaction concentration data in real time, monitors the concentration values at multiple points during the reaction process, records the concentration change situation in the differential stage according to the normal production data and raw material quality information, and generates real-time concentration data;

[0018] The concentration change trend analysis sub-module analyzes the trend of concentration change based on the real-time concentration data and material usage prediction information, combines the raw material quality and dosage, predicts the future concentration change situation, judges whether the current concentration tends to the target concentration range, and calculates the future concentration change rate, and generates concentration change trend data;

[0019] The concentration adjustment calculation sub-module calculates the adjustment values of the current reaction rate and feeding amount by comparing the target concentration with the predicted concentration change according to the concentration change trend data, combines the reaction rate data, adjusts the reaction rate and feeding amount, and generates concentration adjustment information.

[0020] The improvement of the present invention is that the formula for calculating the future concentration change rate is:

[0021]

[0022] where R c represents the future concentration change rate, represents the real-time concentration data at the i-th time point, represents the real-time concentration data at the (i - 1)-th time point, M i represents the raw material dosage at the i-th time point, n represents the total number of time points used for calculation, α is the reference coefficient of the raw material dosage, β is the power exponent of the concentration adjustment factor, and γ is an additional offset parameter.

[0023] The improvement of the present invention is that the temperature real-time control module includes:

[0024] The temperature data acquisition sub-module collects the temperature data at multiple positions of the reaction kettle in real time based on the concentration adjustment information, detects the temperature change in the differential reaction stage, monitors the temperature value and records the real-time data of each position, and generates real-time temperature data;

[0025] The temperature change analysis sub-module analyzes the temperature change trend according to the real-time temperature data, combines the normal reaction data, evaluates the temperature deviation, calculates the temperature change rate, and generates temperature change trend data;

[0026] The temperature adjustment calculation sub-module selects the corresponding temperature control strategy according to the temperature change trend data, combines the reaction stage and temperature change trend, adjusts the heating rate and temperature accuracy, and adjusts the temperature to be maintained within the set range to obtain temperature adjustment information.

[0027] The improvement of the present invention is that the production data analysis module includes:

[0028] Based on the temperature adjustment information, the temperature monitoring sub-module obtains the real-time temperature data during the phosphate chemical production process, compares the temperature data with the set temperature reference value, judges the temperature deviation value of each production link, and calculates the temperature deviation coefficient;

[0029] The pressure and flow monitoring sub-module obtains the real-time pressure and flow data during the phosphate chemical production process, compares them with the set pressure reference value and flow reference value respectively, calculates the pressure and flow deviations of each production link, and obtains the pressure and flow deviation value;

[0030] Based on the temperature deviation coefficient and the pressure and flow deviation value, the deviation degree calculation sub-module evaluates the deviation degree of each link and generates production deviation data.

[0031] The improvement of the present invention is that the formula for evaluating the deviation degree of each link is:

[0032]

[0033] where D j represents the deviation degree of the jth production link, represents the actual temperature value of the jth link, represents the set temperature value of the jth link, represents the actual pressure value of the jth link, represents the set pressure value of the jth link, represents the actual flow value of the jth link, represents the set flow value of the jth link, α re is the temperature deviation adjustment coefficient, β re is the pressure deviation adjustment coefficient, γ re is the flow deviation adjustment coefficient.

[0034] The improvement of the present invention is that the system further includes:

[0035] Based on the production deviation data, the deviation correction module analyzes the deviation degree of each production link, judges whether it exceeds the allowable deviation range, adjusts the resource allocation and control strategy for the deviation exceeding the allowable range, corrects the deviation, and obtains the deviation correction information;

[0036] The deviation correction information includes resource allocation adjustment information, scheduling strategy adjustment, and allowable deviation range.

[0037] The improvement of the present invention is that the deviation correction module includes:

[0038] Based on the production deviation data, the deviation detection sub-module obtains the deviation value of each production link, determines whether each deviation value exceeds the set allowable deviation range. If it exceeds the range, it marks the link as a link that needs to be corrected, and generates a list of links with excessive deviations.

[0039] Based on the list of links with excessive deviations, the resource adjustment sub-module mobilizes production resources for optimal allocation. According to the goals and requirements of resource allocation, it performs resource reallocation and adjusts control strategies, generating resource adjustment information.

[0040] Based on the resource adjustment information, the deviation correction sub-module corrects the production links that exceed the allowable deviation range, adjusts the corresponding production parameters and production conditions, and generates deviation correction information.

[0041] Compared with the prior art, the advantages and positive effects of the present invention are as follows:

[0042] In the present invention, through material consumption prediction and concentration adjustment, combined with temperature and flow control, precise adjustment can be carried out in a timely manner to ensure the optimization of production efficiency and quality. By analyzing deviation data and correcting deviations that exceed the allowable range, errors caused by human operation or system deviation during the production process are effectively avoided, the adaptive ability of production is enhanced, product consistency and production stability are optimized, the production parameters of each link can be adjusted in real time to ensure the efficiency and stability of the entire process, and the use of resources is optimized, reducing energy consumption and material waste, making the production process more in line with the requirements of green and sustainable development. Through the coordinated adjustment of multiple production parameters, errors caused by traditional manual intervention are effectively reduced, the automation and intelligent level of the production process are improved, and the efficiency and reliability of the production system are significantly enhanced. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 is the system flow chart of the present invention;

[0044] Figure 2 is the schematic diagram of the system framework of the present invention;

[0045] Figure 3 is the flow chart of the resource demand prediction module of the present invention;

[0046] Figure 4 is the flow chart of the concentration prediction and adjustment module of the present invention;

[0047] Figure 5 is the flow chart of the real-time temperature control module of the present invention;

[0048] Figure 6 is the flow chart of the production data analysis module of the present invention;

[0049] Figure 7This is the flowchart of the deviation correction module of the present invention. Detailed implementation manners

[0050] In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0051] In the description of the present invention, it should be understood that the orientation or positional relationships indicated by the terms "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. are based on the orientation or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as limiting the present invention. In addition, in the description of the present invention, the meaning of "a plurality of" is two or more, unless otherwise specifically defined.

[0052] Please refer to Figure 1 , the present invention provides a technical solution: a high-quality phosphate chemical process automation system, the system includes:

[0053] The resource demand prediction module obtains the production records of phosphate chemical industry, extracts the current production target and raw material quality information, combines the material usage data in the normal production mode, analyzes the raw material consumption trend under different production targets, and calculates the consumption and usage trend of the required materials based on the current production target and raw material quality, and generates material usage prediction information;

[0054] The concentration prediction and adjustment module, based on the material usage prediction information, collects real-time reaction concentration data, analyzes the concentration change trend, combines the raw material quality and dosage, predicts the future concentration change, calculates the adjustment values of the reaction rate and the feeding amount according to the target concentration and the predicted concentration change trend, and adjusts the concentration to be kept within the set range to obtain concentration adjustment information;

[0055] The temperature real-time control module, based on the concentration adjustment information, collects the temperature data at multiple positions of the reaction kettle in real time, combines the normal reaction data, analyzes the temperature change trend, and selects the corresponding temperature control strategy according to the reaction stage, adjusts the heating rate and temperature accuracy, and keeps the temperature change within the set range to obtain temperature adjustment information;

[0056] The production data analysis module, based on the temperature adjustment information, collects the key production data in the phosphate chemical production process, including temperature, pressure and flow rate, monitors the real-time changes of each parameter, compares with the set reference values, and obtains the deviation degree of each production link by comparing the deviation values to obtain production deviation data;

[0057] Based on the production deviation data, the deviation correction module analyzes the deviation degree of each production link, determines whether it exceeds the allowable deviation range, adjusts the resource allocation and control strategy for the deviation exceeding the allowable range, corrects the deviation, and obtains the deviation correction information.

[0058] The material usage prediction information includes the raw material type, predicted usage amount, and usage trend. The concentration adjustment information includes the reaction rate adjustment amount, feeding amount adjustment value, and concentration change range. The temperature adjustment information includes the heating rate, temperature accuracy, and temperature control strategy. The production deviation data includes the temperature deviation value, pressure deviation value, and flow deviation value. The deviation correction information includes the resource allocation adjustment information, scheduling strategy adjustment, and allowable deviation range.

[0059] Please refer to Figure 2 and Figure 3 , the resource demand prediction module includes:

[0060] The production data extraction sub-module obtains the phosphate chemical production records, extracts the current production target and raw material quality information, and combines with the material usage data in the normal production mode to obtain the benchmark data set;

[0061] The production data extraction sub-module obtains the phosphate chemical production records. First, it retrieves information including production date, production line number, shift number, raw material type, raw material incoming batch number, single batch raw material quality indicators (including P2O5 content, particle size distribution, moisture content, impurity types and their concentrations, etc.), product grade, product target parameters (such as purity, color, density, output) and other fields from the historical production record database. For each production record, it extracts the raw material type and its quality parameters item by item, and at the same time extracts the corresponding production target parameters and establishes a structured mapping relationship in the system. Then it matches the material usage data of this production target in the normal production mode, that is, taking this production target as the screening condition, selects records with a production stability score higher than 85 points from the historical data and sets this stability threshold. This score is based on indicators such as temperature fluctuation range less than ±2°C, material flow deviation lower than ±3%, equipment continuous operation time exceeding 72 hours, energy consumption volatility less than ±5%. Through the above screening operations, a production stable sample set is formed. The raw material types, single batch usage amounts, raw material combination ratios, input time nodes, reaction duration, and corresponding output efficiency data used in this sample set are unified and merged to form a data table. Subsequently, all table items are clustered by production target, and a material usage data cluster is constructed for each target. For multiple records within the same target, the expected value of each raw material quality indicator is obtained by weighted average, where the weighting coefficient is allocated according to the reaction yield of each record. Suppose in the records corresponding to target A, the yield of the first record is 90% and the second is 85%, then the weighting coefficients are 0.514 and 0.486. Apply the formula:

[0062] μ k = ∑(r i ·x ik ) / ∑r i ;

[0063] r i is the yield of the i-th record, x ik is the k-th index in the i-th record, and μ k is the reference value of the k-th raw material quality index under this target. Based on this, the extraction of the reference values of the raw material quality indexes under multiple targets is completed, and finally a reference dataset containing multiple targets and their respective raw material index means and usage amounts is formed.

[0064] Based on the reference dataset, the raw material consumption analysis sub-module analyzes the raw material consumption trends under multiple production targets, calculates the consumption ratios of raw materials in each stage, and generates raw material consumption trend data;

[0065] Based on the reference dataset, the raw material consumption analysis sub-module extracts the raw material usage combinations and corresponding usage amounts associated with a specific production target. By using the production stage identification field set in the record, the complete production process is divided into three stages: the pretreatment stage, the main reaction stage, and the post-treatment stage. Then, the types of raw materials used in each stage are counted item by item. The usage amounts of each raw material in each stage are statistically counted in segments in the form of labels to construct a phased consumption matrix. Subsequently, the matrix is normalized row by row to obtain the consumption ratios of each raw material in each stage. This ratio value is defined as the single-stage raw material usage divided by the total usage. For example, under Target A, the total usage of a certain raw material is 100 kg, and the usage amount in the main reaction stage is 65 kg. Then the ratio in the main reaction stage is 0.65. If there are five types of raw materials, a phased raw material consumption ratio table with a dimension of 3×5 is constructed. Subsequently, the standard deviation of the ratio changes of each type of raw material under different targets is calculated and the raw material consumption trend is output. The trend division criterion is: the standard deviation is less than 0.05 is "stable", between 0.05 - 0.15 is "fluctuating", and greater than 0.15 is "large change", so as to identify the raw materials with significant consumption changes in different production targets, and then clarify the usage tendency of raw materials under different targets. For the same type of raw material combination (such as two different ore sources but both are phosphate rock powders), the point-to-point difference operation is performed on its consumption trend sequence. If the maximum difference exceeds 0.2, it is marked as "significantly different usage patterns", otherwise it is classified as "substitutable combination". Finally, raw material consumption trend data including the types of raw materials, the usage ratios in each stage, the stability label, and the substitution relationship between raw materials under each production target is generated.

[0066] The material consumption estimation sub-module calculates the consumption amount and usage trend of the required materials based on the raw material consumption trend data, combined with the current production target and raw material quality data, and generates material usage prediction information.

[0067] Based on the raw material consumption trend data, the material consumption estimation sub-module first extracts the currently set production target and calls the corresponding reference raw material combination. At the same time, it obtains the quality data of the currently input raw materials, including parameters such as the mass fraction of P2O5, the contents of impurities Fe2O3 and Al2O3, and the mass fraction of moisture. Quality adjustment coefficients are assigned to various raw materials according to the raw material quality indicators. This coefficient is used to measure the difference between the current raw material quality and the reference raw material. The adjustment coefficient is set as follows: when the mass fraction of P2O5 is 3% lower than the reference value, it is assigned 0.9; when it is 1%-3% lower than the reference value, it is assigned 0.95; when it is equal to or higher than the reference value, it is assigned 1. For other impurities, if they exceed the reference value by 1%, the adjustment coefficient is reduced by 0.02 for each 1% exceeded. Calculate the adjustment coefficient c of each type of raw material accordingly. i , and then combine it with the reference usage amount b i , and calculate the currently recommended usage amount as m i = b i / c i , for example, if the reference usage amount of a certain raw material is 40 kg and the adjustment coefficient is 0.95, then the recommended amount is 42.1 kg. Subsequently, according to the usage ratios of each type of raw material in the three stages in the raw material consumption trend data, it is proportionally allocated to each stage to construct a material usage sequence, and further calculate the instantaneous feeding rate within the time window required for each stage. The feeding rate v = stage recommended usage amount / stage time span. For example, if the stage recommended usage amount is 21 kg and the stage time is 6 hours, then the rate is 3.5 kg / h. Finally, generate material usage prediction information. The information fields include: target number, raw material number, adjustment coefficient, stage recommended usage amount, instantaneous feeding rate, raw material combination usage deviation rate, etc.

[0068] Please refer to Figure 2 and Figure 3 , the concentration prediction and adjustment module includes:

[0069] The concentration data acquisition sub-module obtains the material usage prediction information and real-time collects the reaction concentration data, monitors the concentration values at multiple points during the reaction process, records the concentration change situation in the differential stage according to the normal production data and raw material quality information, and generates real-time concentration data;

[0070] The concentration data acquisition sub-module obtains the material usage prediction information, and collects the reaction concentration data in real time, monitors the concentration values at multiple points during the reaction. The data collected in real time includes the concentration values at different positions in the reaction kettle, such as the concentration sensor data at different points like the top, middle, bottom, etc. These data are uploaded to the central control system in real time through the PLC (Programmable Logic Controller). The system synchronously analyzes the concentration data to determine whether the concentration is within the normal range. At the same time, it compares the current reaction concentration data with the predicted data to check whether it meets the expectations. If there is a significant difference between the actual concentration and the predicted concentration, the system will trigger an alarm and record the concentration change situation during the differential stage. The system automatically analyzes the amplitude of the concentration change based on the raw material usage and quality, combined with other factors such as reaction time, temperature, pressure, etc. If it is found that the concentration during the reaction deviates greatly from the target range, a real-time concentration data report will be generated, and the time, concentration change, and stage data will be recorded for subsequent adjustment of reaction conditions or optimization of raw material ratio. Finally, a concentration change trend chart will be formed to show the difference between the real-time concentration fluctuation and the predicted value, which is convenient for further adjustment of the production process.

[0071] The concentration change trend analysis sub-module analyzes the trend of concentration change based on the real-time concentration data and the material usage prediction information, combines the raw material quality and usage, predicts the future concentration change situation, determines whether the current concentration tends to the target concentration range, and calculates the future concentration change rate to generate the concentration change trend data;

[0072] The formula for calculating the future concentration change rate is:

[0073]

[0074] where R c represents the future concentration change rate, represents the real-time concentration data at the i-th time point, represents the real-time concentration data at the (i - 1)-th time point, M i represents the raw material usage at the i-th time point, n represents the total number of time points used for calculation, α is the reference coefficient of the raw material usage, β is the power exponent of the concentration adjustment factor, and γ is an additional offset parameter;

[0075] The concentration change trend analysis sub-module, based on real-time concentration data and material usage prediction information, first extracts historical concentration data for comparison with current real-time data, calculates the concentration change value at each time point, correlates the concentration change at each time point with the raw material usage, extracts the corresponding raw material quality information, such as the P2O5 content, impurity distribution, particle size, etc. currently input, and predicts the future concentration change situation by comparing the concentration change trends in the dataset and combining the physical and chemical conditions (such as temperature, pressure, flow rate, etc.) at each stage of the reaction process. In the specific operation process, if the concentration change value at a certain stage is greater than the set error range of the target concentration (for example, the target concentration is 0.85 mol / L, and the current concentration error exceeds ±5%, that is, 0.8075 mol / L to 0.8925 mol / L), it is considered that the concentration fluctuates; on this basis, based on the past reaction history and combined with the trend curve of the concentration change, the system will further judge whether the current concentration tends to the target concentration range. If it deviates from the target range, a concentration adjustment requirement report will be generated and a warning will be issued; in addition, the system calculates the future concentration change rate to identify whether there is a risk of unstable concentration in the current reaction process. The specific calculation steps are as follows: judge the concentration change rate R through the historical data and the fluctuation amount of the current concentration point c , specifically, calculate the absolute value of the concentration difference value at each time point, multiply it by the power exponent of the raw material usage at the corresponding time point and the reference coefficient, and finally divide it by the sum of the usage amounts at all time points plus the offset parameter. The formula is as follows:

[0076]

[0077] Where: represents the real-time concentration data at the i-th time point, represents the real-time concentration data at the (i - 1)-th time point, M i represents the raw material usage at the i-th time point, α is the reference coefficient of the raw material usage, β is the power exponent of the concentration adjustment factor, γ is the additional offset parameter, n is the total number of time points participating in the calculation, and R c represents the future concentration change rate;

[0078] Actual calculation example:

[0079] It is set that the system monitors the concentration change from the start time point t0 to the time point t4 (5 time points) of the reaction, and the given real-time concentration data is:

[0080]

[0081] The corresponding raw material usages are: M0 = 50 kg, M1 = 55 kg, M2 = 58 kg, M3 = 60 kg, M4 = 62 kg;

[0082] The reference coefficient is: α = 1.2, the concentration adjustment factor is: β = 1.1, and the offset parameter is: γ = 0.5.

[0083] Calculation steps:

[0084] Calculate the absolute value of the concentration difference:

[0085]

[0086]

[0087] Calculate the weighted value at each time point:

[0088]

[0089] Calculate the concentration change rate:

[0090]

[0091] The final concentration change rate is 0.0149 mol / L·kg -1 , which means that within the given time range, the trend of concentration change is the concentration increase per unit change in the amount of raw material used.

[0092] Based on the concentration change trend data, combined with the reaction rate data, the concentration adjustment calculation sub-module calculates the adjustment values of the current reaction rate and the feeding amount by comparing the target concentration with the expected concentration change, adjusts the reaction rate and the feeding amount, and generates concentration adjustment information.

[0093] Based on the concentration change trend data, combined with the reaction rate data, the concentration adjustment calculation sub-module calculates the adjustment values of the current reaction rate and the feeding amount by comparing the target concentration with the expected concentration change. The specific process is as follows: First, calculate the concentration error in the current reaction process based on the target concentration and the actual concentration change rate, and adjust the reaction rate based on this error. If the concentration is too low, it may be necessary to increase the feeding amount and feeding rate of the raw material; otherwise, adjust the reaction rate to reduce unnecessary raw material consumption. The system automatically calculates the adjustment values of the reaction rate and the feeding amount through the preset adjustment coefficient, combined with the concentration change rate. Assuming the target concentration is 0.85 mol / L, the actual concentration is 0.75 mol / L, the concentration error is 0.10 mol / L, and the concentration change rate R c is 0.0149, then the reaction rate adjustment coefficient may be 1.2 times, indicating that the reaction rate needs to be increased by 20%. The system automatically applies this adjustment value to actual production, and finally generates concentration adjustment information, including the recommended values of the reaction rate adjustment amount and the feeding amount, and automatically transmits them to the operation interface for execution to ensure that the reaction reaches the optimal concentration level.

[0094] Please refer to Figure 2 and Figure 5, the temperature real-time control module includes:

[0095] The temperature data acquisition sub-module, based on the concentration adjustment information, collects the temperature data at multiple positions of the reactor in real time, detects the temperature changes in different reaction stages, monitors the temperature values and records the real-time data of each position, and generates real-time temperature data.

[0096] The temperature data acquisition sub-module, based on the concentration adjustment information, collects the temperature data at multiple positions of the reactor in real time, monitors the temperature values at different positions during the reaction process. The data acquisition is realized through a temperature sensor system, which arranges multiple temperature sensors at multiple positions of the reactor to collect the temperature change data in the reactor in real time. The temperature sensors are installed at multiple different positions such as the top, middle, and bottom of the reactor and are connected to the data acquisition unit. The data acquisition unit transmits the real-time temperature data to the central control system. The control system synchronously records the data and checks whether the data collected by each sensor meets the set response range. If the temperature at a certain position exceeds the set warning threshold (for example, the threshold is set to 100 °C), the event will be immediately recorded and an alarm will be issued. At the same time, if significant temperature fluctuations are monitored in this area at multiple time points, the system will further analyze the data, record the temperature change trend, form real-time temperature data and store it for subsequent analysis to ensure that the temperature changes in each reaction stage can be effectively tracked, so as to provide support for temperature control decisions, and finally generate a detailed report containing temperature data. The report content includes the temperature fluctuation range, the average temperature at different positions, the temperature change trend, and the diagnostic data of abnormal fluctuations.

[0097] The temperature change analysis sub-module analyzes the temperature change trend, evaluates the temperature deviation, calculates the temperature change rate, and generates temperature change trend data according to the real-time temperature data and combined with the normal reaction data.

[0098] The temperature change analysis sub-module, according to the real-time temperature data and combined with the normal reaction data, first extracts the temperature data at different time points and compares them with the normal reaction data to analyze the temperature change trend. First, calculate the temperature difference within each time period, and then determine the temperature deviation in the current reaction process by comparing with the normal reaction data. The temperature deviation can be calculated by comparing the temperature at the current time point with the expected temperature in the historical data. Set the standard temperature value during the reaction process in the historical data to 90 °C, and the temperature data of the current reaction is 92 °C, then the temperature deviation is 2 °C. On this basis, analyze the temperature change rate. The temperature change rate is defined as the temperature change amount per unit time, and the calculation formula is the temperature change rate where ΔT is the temperature change amount and Δt is the time interval. If the temperature changes from 90 °C to 92 °C from time point t₁ = 0 hour to t₂ = 1 hour, then the temperature change rate v t is During the calculation process, data from multiple time periods are combined to finally form temperature change trend data, including the temperature deviation range, change rate, and whether the predetermined temperature control standard is reached, and a temperature change trend chart is generated to help further analyze the impact of temperature fluctuations on the reaction process.

[0099] Based on the temperature change trend data, the temperature adjustment calculation sub-module selects the corresponding temperature control strategy, combines the reaction stage and the temperature change trend, adjusts the heating rate and temperature accuracy, and adjusts the temperature to be maintained within the set range to obtain temperature adjustment information.

[0100] Based on the temperature change trend data, the temperature adjustment calculation sub-module selects the corresponding temperature control strategy. First, according to the temperature deviation and change rate in the temperature change trend data, it judges whether it is necessary to adjust the heating rate and temperature control accuracy. If the temperature deviation exceeds the set threshold (such as the set temperature fluctuation range is ±2°C), it is necessary to increase the response speed of the temperature control strategy and adjust the heating rate according to different reaction stages (such as the pretreatment stage, main reaction stage, and post-treatment stage). The system automatically selects the appropriate temperature control strategy according to the temperature requirements of each stage. If the current stage temperature is low and the change rate is fast (such as the change rate is greater than 5°C / hour), the system will select a higher heating rate for rapid heating. Conversely, if the temperature change is stable, the heating rate is adjusted to a lower value to avoid overheating. The temperature accuracy adjustment is based on the deviation of the current temperature. If the temperature deviation is large, a higher temperature adjustment accuracy is required (such as the error range is less than ±0.5°C). If the deviation is small, the adjustment accuracy is appropriately reduced. Further, according to the set target temperature range (such as 80°C to 85°C) and the actually measured temperature (such as the current temperature is 83°C), the temperature control parameters to be adjusted are calculated. Finally, the heating rate is adjusted to the target range to form temperature adjustment information, including the heating rate, accuracy requirements, and specific adjustment plan after temperature adjustment, and it is automatically transmitted to the operation interface for execution to ensure that the temperature is maintained within the set range.

[0101] Please refer to Figure 2 and Figure 6 , the production data analysis module includes:

[0102] Based on the temperature adjustment information, the temperature monitoring sub-module obtains the real-time temperature data during the phosphate chemical production process, compares the temperature data with the set temperature reference value, judges the temperature deviation value of each production link, and calculates the temperature deviation coefficient.

[0103] Based on the temperature adjustment information, the temperature monitoring sub-module first obtains the real-time temperature data during the phosphate chemical production process. The temperature data is collected by multiple temperature sensors installed at different positions of the reaction kettle. These sensors are distributed at various key points of the reaction kettle, such as the top, middle, bottom, etc., to ensure coverage of the entire reaction area and real-time monitoring of the temperature changes at each position. These data are transmitted to the central control system through the PLC system. In the system, the temperature value at each time point is compared with the set temperature reference value. The set temperature reference value is obtained based on historical data, optimal reaction conditions, and production goals. For example, the set reference temperature may be 85°C. If there is a difference between the actual temperature value and the reference temperature value, the temperature deviation value will be calculated. The temperature deviation coefficient is the ratio of the difference between the actual temperature and the set reference temperature to the reference temperature. Suppose the set temperature for a certain production link is 85°C and the actual measured temperature is 87°C, then the temperature deviation is 2°C, and at this time the temperature deviation coefficient is Next, the system will judge whether it deviates from the temperature requirements during the production process according to the temperature deviation coefficients of each link, and record the temperature change information, including the temperature fluctuation conditions of each link, and generate a real-time temperature data report.

[0104] The pressure and flow monitoring sub-module obtains the real-time pressure and flow data during the phosphate chemical production process, compares them with the set pressure reference value and flow reference value respectively, calculates the pressure and flow deviations of each production link, and obtains the pressure and flow deviation values;

[0105] The pressure and flow monitoring sub-module obtains the real-time pressure and flow data during the phosphate chemical production process. The pressure and flow data are collected by pressure sensors and flow meters. The pressure sensors and flow meters are installed at the feed inlet of the reaction kettle, the outlet inside the reactor, and other important positions to monitor the pressure and flow conditions during the whole reaction process. The real-time collected pressure and flow data are compared with the pre-set reference values. The set reference pressure and flow values are usually set according to historical production data or standard production models. For example, the set reference pressure may be 5 MPa and the reference flow is 100 L / min. If the actual measured pressure is 4.8 MPa and the flow is 98 L / min, then according to the differences between these values and the reference values, the pressure and flow deviations of each production link are calculated. The pressure deviation is 5 - 4.8 = 0.2 MPa, and the flow deviation is 100 - 98 = 2 L / min. Calculate the percentages of the pressure deviation and the flow deviation. The percentage of the pressure deviation is The percentage of the flow deviation is Finally, the pressure and flow deviation values of each production link are obtained, these deviations are recorded, and a pressure and flow deviation data report is generated to provide support for subsequent analysis.

[0106] The deviation calculation sub-module evaluates the deviation of each link based on the temperature deviation coefficient and the pressure-flow deviation value, and generates production deviation data.

[0107] The formula for evaluating the deviation of each link is:

[0108]

[0109] where D j represents the deviation of the j-th production link, represents the actual temperature value of the j-th link, represents the set temperature value of the j-th link, represents the actual pressure value of the j-th link, represents the set pressure value of the j-th link, represents the actual flow value of the j-th link, represents the set flow value of the j-th link, α re is the temperature deviation adjustment coefficient, β re is the pressure deviation adjustment coefficient, γ re is the flow deviation adjustment coefficient.

[0110] Based on the temperature deviation coefficient and the pressure-flow deviation value, the deviation calculation sub-module first normalizes the temperature deviation, pressure deviation, and flow deviation of each link according to the set adjustment coefficients. The temperature deviation, pressure deviation, and flow deviation are weighted and adjusted through their respective adjustment coefficients. The set temperature deviation adjustment coefficient is α re = 0.1, the pressure deviation adjustment coefficient is β re = 0.2, the flow deviation adjustment coefficient is γ re = 0.15. Then, the system performs a normalization calculation on the deviation values through the above coefficients. When the temperature deviation coefficient is 0.0235, the pressure deviation is 0.04, and the flow deviation is 0.02, the system substitutes them into the following comprehensive deviation formula:

[0111]

[0112] where is the actual temperature value of the j-th link, is the set temperature value of the j-th link, is the actual pressure value of the j-th link, is the set pressure value of the j-th link, is the actual flow value of the j-th link, is the set flow value of the j-th link, α re is the temperature deviation adjustment coefficient, β re is the pressure deviation adjustment coefficient, γ reis the flow deviation adjustment coefficient. After substituting specific data, the calculation of the deviation degree is as follows:

[0113]

[0114] Therefore, the deviation degree of the j-th production link is 0.336, and a corresponding production deviation data report is generated. The report contains the deviation degree data of each production link and provides a guiding basis for the adjustment of the subsequent production process.

[0115] Please refer to Figure 2 and Figure 7 , the deviation correction module includes:

[0116] Based on the production deviation data, the deviation detection sub-module obtains the deviation value of each production link, determines whether each deviation value exceeds the set allowable deviation range. If it exceeds the range, the link is marked as a link that needs to be corrected, and a list of deviation-exceeding links is generated;

[0117] Based on the production deviation data, the deviation detection sub-module first obtains the deviation value of each production link. The deviation value is calculated according to the differences between the actual temperature, pressure, flow rate, etc. of each production link and the set reference value. For example, the set temperature reference value is 85°C, and the actual temperature of a certain link is 87°C, then the temperature deviation of this link is 2°C; the set pressure reference value is 5 MPa, and the actually measured pressure is 4.8 MPa, then the pressure deviation is 0.2 MPa; the set flow rate reference value is 100 L / min, and the actual flow rate is 98 L / min, the flow rate deviation is 2 L / min. These deviation values are recorded and summarized in the production deviation data. Then, through the set allowable deviation range (for example, the temperature allowable deviation range is ±3°C, the pressure is ±0.5 MPa, and the flow rate is ±5 L / min), the deviation value of each production link is judged. If the deviation value of a certain production link exceeds the allowable range, the system will mark this link as a link that needs to be corrected. For example, if the actual temperature is 87°C and the set temperature is 85°C, and the deviation is 2°C, then the temperature deviation of this link does not exceed the set ±3°C range and is not marked as a link that needs to be corrected; if the pressure deviation is 0.6 MPa, which exceeds the allowable range, then this link is marked as an over-standard link and needs to be corrected. Finally, a list of deviation-exceeding links is generated, which includes all links that exceed the allowable deviation range for the subsequent use of resource adjustment and deviation correction module.

[0118] Based on the list of deviation-exceeding links, the resource adjustment sub-module mobilizes production resources for optimal allocation, executes resource reallocation and adjusts control strategies according to the goals and requirements of resource allocation, and generates resource adjustment information;

[0119] The resource adjustment sub-module mobilizes production resources for optimal allocation according to the list of out-of-specification links. First, the system will check the list of out-of-specification links and reconfigure resources based on the actual requirements of each out-of-specification link. For example, if a large pressure deviation is detected in a certain production link, pressure regulating equipment needs to be added, or a more efficient heating device is required for the temperature control device in that link. The system will analyze the availability of existing resources according to the resource requirements of each link and formulate an optimal allocation plan. The resources to be mobilized are set to include compressors, heaters, flow control valves, etc. The system will evaluate factors such as the load capacity, operating efficiency, and resource allocation of existing equipment and arrange the resource allocation reasonably. If the pressure in a certain link is too low and exceeds the set allowable range, more compressors may need to be added or the system working pressure may need to be increased; if the temperature is too high, the system may need to reduce the heater output or adjust the accuracy of the temperature sensor. Based on the specific requirements of each link, the resource adjustment module will formulate a reasonable control strategy, prioritize the allocation of equipment, and set the priority of equipment use in case of resource shortage. Finally, resource adjustment information will be generated, and the report content includes the types, quantities, allocation methods of the mobilized resources, and the adjusted control strategy.

[0120] The deviation correction sub-module corrects the production links that exceed the allowable deviation range according to the resource adjustment information, adjusts the corresponding production parameters and production conditions, and generates deviation correction information.

[0121] The deviation correction sub-module corrects the production links that exceed the allowable deviation range according to the resource adjustment information. First, the system will select appropriate adjustment measures according to the resource adjustment information. For example, if the temperature deviation in a certain production link is too large, temperature correction needs to be carried out by increasing the heat source or adjusting the temperature sensor in the reactor. If the pressure deviation in a certain link is large, the system will achieve pressure correction by adding a compressor or adjusting the output pressure of the existing compressor; at the same time, production parameters such as heating rate, feed flow rate, and reaction pressure need to be readjusted during the correction process to ensure that the corrected production link meets the set target requirements for temperature, pressure, flow rate, etc. For example, if the temperature deviation in a certain link is 5°C, the actual temperature is 90°C, and the set target temperature is 85°C, the correction plan may include reducing the heater output by 5% or increasing the coolant flow rate; if the pressure deviation is 0.6 MPa, exceeding the set range of ±0.5 MPa, the correction plan may include increasing the compressor output pressure by 2% or adjusting the gas flow rate. Finally, deviation correction information will be generated, which includes the adjusted production conditions, equipment changes during the adjustment process, and the final adjustment results of each link.

[0122] The above are only the preferred embodiments of the present invention and do not limit the present invention in other forms. Any person skilled in the relevant art may use the technical content disclosed above to make changes or modifications into equivalent embodiments with equivalent changes and apply them to other fields. However, as long as it does not depart from the technical solution content of the present invention, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention still fall within the protection scope of the technical solution of the present invention.

Claims

1. An automated system for high-quality phosphate chemical processes, characterized in that, The system includes: The resource demand prediction module obtains the production records of phosphate chemical industry, extracts the current production targets and raw material quality information, analyzes the raw material consumption trends under different production targets, and calculates the consumption quantity and usage trends of the required materials based on the current production targets and raw material quality, generating material usage prediction information; The concentration prediction and adjustment module, based on the material usage prediction information, collects real-time reaction concentration data, analyzes the concentration change trends, predicts future concentration changes, and calculates the adjustment values of the reaction rate and feeding quantity according to the target concentration and the predicted concentration change trends, obtaining concentration adjustment information; The temperature real-time control module, based on the concentration adjustment information, collects the temperature data at multiple positions of the reaction kettle in real time, combines the normal reaction data, analyzes the temperature change trends, and selects the corresponding temperature control strategy according to the reaction stage, adjusting the heating rate and temperature accuracy, obtaining temperature adjustment information; The production data analysis module, based on the temperature adjustment information, collects the key production data in the process of phosphate chemical production, monitors the real-time changes of each parameter, and compares them with the set reference values to obtain the deviation degree of each production link, obtaining production deviation data.

2. The high-quality phosphate chemical process automation system according to claim 1, wherein The material usage prediction information includes the types of raw materials, predicted usage quantities, and usage trends. The concentration adjustment information includes the adjustment quantity of the reaction rate, the adjustment value of the feeding quantity, and the concentration change range. The temperature adjustment information includes the heating rate, temperature accuracy, and temperature control strategy. The production deviation data includes the temperature deviation value, pressure deviation value, and flow deviation value.

3. The high-quality phosphate chemical process automation system according to claim 2, wherein, The resource demand prediction module includes: The production data extraction sub-module obtains the production records of phosphate chemical industry, extracts the current production targets and raw material quality information, and combines the material usage data in the normal production mode to obtain a reference data set; The raw material consumption analysis sub-module, based on the reference data set, analyzes the raw material consumption trends under multiple production targets, calculates the consumption ratio of raw materials in each stage, and generates raw material consumption trend data; The material consumption calculation sub-module, according to the raw material consumption trend data, combines the current production targets and raw material quality data, calculates the consumption quantity and usage trends of the required materials, and generates material usage prediction information.

4. The high-quality phosphate chemical process automation system according to claim 3, characterized in that, The concentration prediction and adjustment module includes: The concentration data collection sub-module obtains the material usage prediction information, collects the reaction concentration data in real time, monitors the concentration values at multiple points during the reaction process, and records the concentration change conditions in different stages according to the normal production data and raw material quality information, generating real-time concentration data; The concentration change trend analysis sub-module, based on the real-time concentration data and material usage prediction information, analyzes the concentration change trends, combines the raw material quality and usage, predicts the future concentration change conditions, determines whether the current concentration tends to the target concentration range, and calculates the future concentration change rate, generating concentration change trend data; The concentration adjustment calculation sub-module, according to the concentration change trend data, combines the reaction rate data, and calculates the adjustment values of the current reaction rate and feeding quantity by comparing the target concentration with the predicted concentration change, adjusting the reaction rate and feeding quantity, and generating concentration adjustment information.

5. The high-quality phosphate chemical process automation system according to claim 4, wherein, The formula for calculating the future concentration change rate is: Among them, R c represents the future change rate of the concentration, represents the real-time concentration data at the i-th time point, represents the real-time concentration data at the (i - 1)-th time point, M i represents the raw material usage at the i-th time point, n represents the total number of time points for calculation, α is the reference coefficient of the raw material usage, β is the power exponent of the concentration adjustment factor, and γ is an additional offset parameter.

6. The high-quality phosphate chemical process automation system according to claim 5, wherein, The real-time temperature control module includes: The temperature data acquisition sub-module, based on the concentration adjustment information, acquires the temperature data at multiple positions of the reactor in real time, detects the temperature changes in different reaction stages, monitors the temperature values and records the real-time data of each position, and generates real-time temperature data; The temperature change analysis sub-module analyzes the temperature change trend, evaluates the temperature deviation, calculates the temperature change rate according to the real-time temperature data and in combination with the normal reaction data, and generates temperature change trend data; The temperature adjustment calculation sub-module selects the corresponding temperature control strategy according to the temperature change trend data, combines the reaction stage and the temperature change trend, adjusts the heating rate and temperature accuracy, and adjusts the temperature to be maintained within the set range to obtain temperature adjustment information.

7. The high-quality phosphate chemical process automation system according to claim 6, wherein The production data analysis module includes: The temperature monitoring sub-module, based on the temperature adjustment information, acquires the real-time temperature data in the phosphate chemical production process, compares the temperature data with the set temperature reference value, judges the temperature deviation value of each production link, and calculates the temperature deviation coefficient; The pressure and flow monitoring sub-module acquires the real-time pressure and flow data in the phosphate chemical production process, compares them with the set pressure reference value and flow reference value respectively, calculates the pressure and flow deviations of each production link, and obtains the pressure and flow deviation values; The deviation degree calculation sub-module evaluates the deviation degree of each link based on the temperature deviation coefficient and the pressure and flow deviation values, and generates production deviation data.

8. The high-quality phosphate chemical process automation system according to claim 7, characterized in that The formula for evaluating the deviation degree of each link is: Among them, D j represents the deviation degree of the j-th production link, represents the actual temperature value of the j-th link, represents the set temperature value of the j-th link, represents the actual pressure value of the j-th link, represents the set pressure value of the j-th link, represents the actual flow value of the j-th link, represents the set flow value of the j-th link, α re is the temperature deviation adjustment coefficient, β re is the pressure deviation adjustment coefficient, γ re is the flow deviation adjustment coefficient.

9. The high-quality phosphate chemical process automation system according to claim 8, characterized in that, The system further includes: The deviation correction module analyzes the deviation degree of each production link based on the production deviation data, judges whether it exceeds the allowable deviation range, and for the deviation that exceeds the allowable range, adjusts the resource allocation and control strategy to correct the deviation and obtains deviation correction information; The deviation correction information includes resource allocation adjustment information, scheduling strategy adjustment, and allowable deviation range.

10. The high-quality phosphate chemical process automation system according to claim 9, characterized in that, The deviation correction module includes: The deviation detection sub-module, based on the production deviation data, acquires the deviation value of each production link, judges whether each deviation value exceeds the set allowable deviation range, and if it exceeds the range, marks the link as a link that needs to be corrected, and generates a list of deviation-exceeding links; The resource adjustment sub-module, according to the list of deviation-exceeding links, mobilizes the production resources for optimal allocation, and according to the goals and requirements of the resource allocation, executes the resource reallocation and adjusts the control strategy to generate resource adjustment information; The deviation correction sub-module corrects the production links that exceed the allowable deviation range according to the resource adjustment information, adjusts the corresponding production parameters and production conditions, and generates deviation correction information.

Images