Intelligent control system and method for prilocaine crystallization equipment

Abstract

The invention relates to the technical field of crystallization equipment intelligent control systems, in particular to a prilocaine crystallization equipment intelligent control system and method.The system comprises a data acquisition layer, a data interaction layer and an application layer, and the data interaction layer comprises a shared database, an intelligent data interaction system and a function module; wherein the shared database is used for storing and managing collected process data and control instructions; the intelligent data interaction system comprises a data acquisition module, a data processing module and an expert system calling module, and the expert system calling module is responsible for decision analysis; the function module comprises a prilocaine crystallization process module, an evaluation criterion module and a comprehensive evaluation method module and is used for providing crystallization process knowledge, evaluation indexes and an optimization method; the whole efficiency and the product quality of the prilocaine crystallization process are remarkably improved, and the method is suitable for large-scale industrial production and can flexibly meet the production requirements of small batches and multiple varieties.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent control systems for crystallization equipment, in particular to an intelligent control system and method for prilocaine crystallization equipment. Background Art

[0002] Prilocaine, an amide local anesthetic, produces a local anesthetic effect by stabilizing nerve cells by blocking the ion flow required for nerve impulse generation and conduction. Prilocaine's chemical structure and local anesthetic effects are similar to lidocaine, but it has a longer duration of action and is less toxic, particularly with lower cardiotoxicity. Therefore, it is commonly used for intravenous regional anesthesia.

[0003] Prilocaine, chemically known as N-(2-methylphenyl)-2-(propylamino)propionamide, is an important local anesthetic. Precise control of its crystallization process has long been a focus of industry attention. In recent years, with the rapid development of automation and information technology, the control systems for prilocaine crystallization equipment have also continued to advance. However, despite the achievements of existing technologies, many problems and challenges remain in practical application.

[0004] Currently, most prilocaine crystallization equipment still uses traditional PID control systems. While simple and easy to implement, these systems often struggle to cope with the complexities of the crystallization process. First, the parameters of PID control systems are typically fixed, making them difficult to adapt to the dynamic changes in the crystallization process. This results in significant fluctuations in the system's control effectiveness during different crystallization stages. Second, traditional systems have limited ability to coordinate control across multiple crystallization equipment, making it difficult to achieve truly optimized configuration. Furthermore, these systems often struggle to process large amounts of real-time data, impacting control accuracy and timeliness.

[0005] On the other hand, while some advanced crystallization control systems have incorporated intelligent algorithms, they often rely on a single algorithm, failing to comprehensively address the multifaceted issues of the crystallization process. For example, some systems employ fuzzy control algorithms to improve control accuracy but neglect energy optimization; others focus on coordinated control of multiple devices but fail to effectively address data noise. This situation, often overlooked in practice, has hindered further optimization of the prilocaine crystallization process.

[0006] Furthermore, most existing control systems utilize a single system architecture, lacking hierarchical and modular design. This not only limits the system's scalability and flexibility, but also makes it difficult to adapt to production environments of varying scales and requirements. In terms of data processing, many systems remain at the stage of simple data collection and storage, failing to fully leverage big data and artificial intelligence technologies to enhance system intelligence.

[0007] In the face of these problems, the industry urgently needs a new intelligent control system for prilocaine crystallization equipment that can comprehensively improve the control accuracy, production efficiency and product quality of the crystallization process. The present invention is proposed to address this need. Summary of the Invention

[0008] The intelligent control system and method for prilocaine crystallization equipment proposed in this paper aims to address many existing problems in the prior art. Through an innovative system architecture and the coordinated application of multiple intelligent algorithms, it achieves comprehensive optimized control of the crystallization process.

[0009] The present invention proposes an intelligent control system for prilocaine crystallization equipment, comprising:

[0010] The intelligent control system of prilocaine crystallization equipment includes a data acquisition layer, a data interaction layer, and an application layer, among which:

[0011] The data acquisition layer includes multiple data acquisition cards and temperature controllers. The data acquisition cards are used to collect temperature, liquid level, and dissolved oxygen parameters during the crystallization process of prilocaine, and feed the collected process data back to the computer through the RS232 interface. The temperature controller receives control signals from the computer through the RS485 interface to control the temperature of each crystallization device. At the same time, it collects crystallization device and process parameters and sends them to the shared database of the data interaction layer.

[0012] The data interaction layer includes a shared database, an intelligent data interaction system, and functional modules, wherein the shared database is used to store and manage collected process data and control instructions; the intelligent data interaction system includes a data acquisition module, a data processing module, and an expert system call module. The data acquisition module is responsible for acquiring data from the shared database, the data processing module filters and performs wavelet transform processing on the data, and the expert system call module is responsible for decision analysis; the functional modules include a prilocaine crystallization process module, an evaluation criteria module, and a comprehensive evaluation method module, which are used to provide crystallization process knowledge, evaluation indicators, and optimization methods;

[0013] The application layer includes a central control computer and a synchronous control computer group. The central control computer is responsible for the planning and scheduling of the entire system, rationally allocates various resources of the system, and can perform manual control. The synchronous control computer group is responsible for executing intelligent control application strategies and independently controlling the crystallization equipment through a shared database.

[0014] Preferably, the data acquisition card of the data acquisition layer adopts the following data filtering algorithm:

[0015] Y(n)=α·X(n)+(1-α)·Y(n-1)

[0016] Among them, Y(n) is the current filtered data, X(n) is the current collected original data, Y(n-1) is the data after the previous filtering, and α is the filter coefficient (0<α<1); by dynamically adjusting the α value, adaptive filtering for different noise levels can be achieved.

[0017] Preferably, the expert system call module of the data interaction layer adopts the following fuzzy logic control algorithm:

[0018]

[0019] Among them, μ A (x) is the membership function, x is the input variable, c is the center of the membership function, a is the width parameter, and b is the shape parameter; by adjusting the c, a, and b parameters, fuzzy control of multiple variables in the crystallization process can be achieved.

[0020] Preferably, the synchronization control computer group of the application layer adopts the following synchronization control algorithm:

[0021]

[0022] in, is the phase adjustment value of the i-th device, K is the synchronization gain coefficient, is the reference phase, is the current phase of the i-th device, and ω0 is the system reference frequency. By dynamically adjusting the K value, precise synchronous control of multiple devices can be achieved.

[0023] Preferably, the comprehensive evaluation method module in the functional module adopts the following multi-objective optimization algorithm:

[0024] F(x)=w1·f1(x)+w2·f2(x)+…+w n ·f n (x)

[0025] Among them, F(x) is the comprehensive evaluation function, f i (x) is the i-th evaluation index function, w i is the weight of the i-th evaluation index (∑w i =1), x is the decision variable vector; by dynamically adjusting w i value, and realize adaptive optimization of different evaluation indicators.

[0026] Preferably, the shared database adopts the following data compression algorithm:

[0027]

[0028] Where C(D) is the compression ratio, H(D) is the entropy of data D, and L(D) is the original length of data D. By minimizing C(D), efficient storage and transmission of large amounts of crystallization process data can be achieved.

[0029] The intelligent control method of prilocaine crystallization equipment of the system comprises the following steps:

[0030] First, the data acquisition card and temperature controller of the data acquisition layer are used to collect the temperature, liquid level, dissolved oxygen and other parameter data during the crystallization of prilocaine;

[0031] Then, the collected data is transmitted to the shared database of the data interaction layer through RS232 and RS485 interfaces;

[0032] Then, the data processing module of the intelligent data interaction system performs filtering and wavelet transformation on the data stored in the shared database;

[0033] Subsequently, the processed data is transferred to the expert system call module, which performs decision analysis using fuzzy logic control algorithm;

[0034] Next, the analysis results are sent to the central control computer at the application layer, which performs planning and scheduling of the overall system;

[0035] Finally, the synchronous control computer group uses the synchronous control algorithm to achieve coordinated control of multiple devices according to the scheduling instructions of the central control computer.

[0036] Preferably, the method further includes the following control decision algorithm:

[0037] u(t)=K(t)·e(t)

[0038] Where u(t) is the control output, K(t) is the adaptive gain, and e(t) is the control error. K(t) is updated according to the following rule:

[0039]

[0040] Among them, γ is the learning rate and sign() is the sign function; by dynamically adjusting K(t), adaptive and precise control of the crystallization process is achieved.

[0041] Preferably, the method further includes the following temperature prediction control algorithm:

[0042]

[0043] Where T(t+Δt) is the predicted temperature after Δt time, T(t) is the current temperature, is the temperature change rate, is the temperature acceleration; by dynamically adjusting Δt, accurate prediction and control of the temperature change during the crystallization process can be achieved.

[0044] Preferably, the method further includes the following load balancing algorithm and distributed optimization algorithm:

[0045] L i (t) = α i Pi(t)+β i ·M i (t)+γ i ·N i (t)

[0046] Among them, L i (t) is the load index of the i-th equipment unit, P i (t) is the processor utilization, M i (t) is the memory utilization, N i (t) is the network utilization rate, α i , β i , γ i is the weight coefficient (α i +β i +γ i =1); by dynamically adjusting α i , β i , γ i Achieve optimal allocation of multi-device resources;

[0047] Distributed optimization algorithm:

[0048] minF(x)=∑f i (x i )

[0049] stg i (x i )≤0, i=1, 2, ..., n

[0050] h(x1, x2, ..., x n )=0

[0051] Among them, F(x) is the global objective function, f i (x i ) is the local objective function of the ith subsystem, g i (x i ) is a local constraint, h(x1, x2, ..., x n ) is the global coupling constraint; by iteratively solving the optimization problems of each subsystem and coordinating the global coupling constraints, the global optimization control of the entire prilocaine crystallization system is achieved.

[0052] The beneficial effects of the present invention are mainly reflected in the following aspects:

[0053] From an overall architectural perspective, the present invention employs a layered design, comprising a data acquisition layer, a data interaction layer, and an application layer. This layered structure not only increases the system's modularity, enhancing its scalability and maintainability, but also achieves a seamless separation between data acquisition, processing, and control, significantly improving the system's overall performance. Data exchange between layers occurs through carefully designed interfaces, ensuring timely data transmission while avoiding unnecessary data redundancy.

[0054] In terms of modular collaboration, the various functional modules of the present invention form a tightly integrated, organic whole. For example, the seamless integration of the data acquisition module and the data processing module ensures the system can acquire high-quality process data in real time. The collaborative operation of the expert system module and the control execution module enables intelligent decision-making and precise control based on empirical knowledge. This inter-module collaboration not only improves the overall efficiency of the system but also enhances its robustness and adaptability.

[0055] This invention also cleverly resolves common technical contradictions in traditional systems. For example, it uses a multi-objective optimization algorithm to find the optimal balance between improving control accuracy and reducing energy consumption. It also uses an adaptive control algorithm to achieve a dynamic balance between achieving rapid response and maintaining system stability. These solutions contribute to the superior performance of this invention in all aspects.

[0056] In terms of effectiveness, the combination of the various technical features of the present invention produces significant complementary, superimposed, and synergistic effects. For example, the combination of the adaptive filtering algorithm and the fuzzy logic control algorithm not only improves data quality but also enhances control accuracy; the synergy of the synchronous control algorithm and the load balancing algorithm achieves efficient collaboration among multiple devices and optimal allocation of resources. The superposition of these effects ultimately manifests as an increase in crystallization yield, an improvement in product purity, a reduction in energy consumption, and enhanced production stability.

[0057] From a macroscopic perspective, this invention significantly improves the overall efficiency and product quality of the prilocaine crystallization process. It is not only suitable for large-scale industrial production, but also flexibly addresses the needs of small-batch, multi-variety production. The enhanced adaptability and intelligence of the system enable it to better cope with changes in raw materials, environmental factors, and other factors, maintaining stable production results.

[0058] From a microscopic perspective, this invention achieves precise control over every step of the crystallization process. From temperature, concentration, stirring speed, to crystallization time, every parameter is maintained at an optimal state under the regulation of intelligent algorithms. This refined control not only improves product quality stability but also provides strong support for process optimization and new product development.

[0059] In summary, this invention, through innovative system design and algorithmic application, comprehensively enhances the control level of prilocaine crystallization equipment, providing a strong guarantee for improving product quality, reducing production costs, and enhancing enterprise competitiveness. Its successful application not only solves many problems currently encountered in prilocaine production, but also provides a useful reference and reference for the intelligent upgrading of the entire pharmaceutical industry. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 It is the overall logic block diagram of the system of the present invention.

[0061] Figure 2 This is a logic block diagram of the data acquisition layer of the present invention.

[0062] Figure 3 This is a logical block diagram of the data interaction layer of the present invention.

[0063] Figure 4 This is a logic block diagram of the application layer of the present invention.

[0064] Figure 5 It is a logic block diagram of the adaptive filtering algorithm of the present invention.

[0065] Figure 6 It is the logic block diagram of the fuzzy logic control algorithm of the present invention.

[0066] Figure 7 It is a logic block diagram of the synchronous control algorithm of the present invention.

[0067] Figure 8 This is a logic block diagram of the multi-objective optimization algorithm of the present invention. DETAILED DESCRIPTION

[0068] To further illustrate the technical means and effects employed by the present invention to achieve its intended objectives, the following detailed description, along with the accompanying drawings and preferred embodiments, includes a detailed description of the specific implementations, structures, features, and effects thereof. In the following description, references to "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.

[0069] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0070] See Figures 1-8 The present invention relates to an intelligent control system and method for prilocaine crystallization equipment, which is mainly used for controlling the crystallization process of prilocaine.

[0071] First, the present invention proposes an intelligent control system for prilocaine crystallization equipment. The system includes a data acquisition layer 1, a data interaction layer 2, and an application layer 3. The data acquisition layer 1 is primarily responsible for collecting various parameter data during the prilocaine crystallization process; the data interaction layer 2 is responsible for data storage, processing, and analysis; and the application layer 3 is responsible for implementing specific control strategies.

[0072] Specifically, the data acquisition layer 1 includes multiple data acquisition cards 11 and a temperature controller 12. The data acquisition cards 11 are connected to a computer via an RS232 interface and are used to collect parameters such as temperature, liquid level, and dissolved oxygen during the prilocaine crystallization process. For example, in one embodiment, the data acquisition cards 11 collect temperature data every 1 second, liquid level data every 5 seconds, and dissolved oxygen data every 10 seconds. This frequency of collection ensures that the system captures changes in the crystallization process in a timely manner while preventing data redundancy.

[0073] The temperature controller 12 is connected to the computer via an RS485 interface and is responsible for controlling the temperature of each crystallization device and collecting crystallization device and process parameters. Preferably, the temperature controller 12 has a control accuracy of ±0.1°C, which is crucial for controlling the crystallization process of prilocaine, as small temperature fluctuations can significantly affect the quality of the crystals.

[0074] Second, the data interaction layer 2 includes a shared database 21, an intelligent data interaction system 22, and functional modules 23. The shared database 21 is used to store and manage collected process data and control instructions. In one embodiment of the present invention, the shared database 21 employs a distributed storage structure, enabling simultaneous processing of data from multiple crystallization devices, significantly improving data processing efficiency.

[0075] The intelligent data interaction system 22 includes a data acquisition module 221, a data processing module 222, and an expert system call module 223. The data acquisition module 221 is responsible for acquiring data from the shared database 21, while the data processing module 222 performs filtering and wavelet transform processing on the data. The expert system call module 223 is responsible for decision analysis. For example, if the system detects abnormal temperature fluctuations during the crystallization process, the expert system call module 223 will quickly make adjustments based on pre-set rules to ensure the stability of the crystallization process.

[0076] Functional modules 23 include a prilocaine crystallization process module 231, an evaluation criteria module 232, and a comprehensive evaluation method module 233, which provide crystallization process knowledge, evaluation indicators, and optimization methods. These modules enable the system to accurately control the crystallization characteristics of prilocaine.

[0077] Next, the application layer 3 includes a central control computer 31 and a synchronous control computer cluster 32. The central control computer 31 is responsible for overall system planning and scheduling, rationally allocating system resources, and enabling manual control. The synchronous control computer cluster 32 is responsible for executing intelligent control application strategies and independently controlling the crystallization equipment through the shared database 21.

[0078] Next, we introduce in detail several key algorithms used in this invention.

[0079] First, the data acquisition card 11 of the data acquisition layer 1 adopts an adaptive filtering algorithm:

[0080] Y(n)=α·X(n)+(1-α)·Y(n-1)

[0081] Among them, Y(n) is the current filtered data, X(n) is the current collected original data, Y(n-1) is the data after the previous filtering, and α is the filter coefficient (0<α<1); by dynamically adjusting the α value, adaptive filtering for different noise levels can be achieved.

[0082] The advantage of this algorithm is that it can achieve adaptive filtering for different noise levels by dynamically adjusting the α value. For example, in the early stages of crystallization, the system will set a larger α value (such as 0.8) to quickly respond to system changes; while in the stable crystallization period, the α value will be lowered (such as 0.2) to obtain smoother data.

[0083] Secondly, the expert system call module 223 of the data interaction layer 2 adopts the fuzzy logic control algorithm:

[0084]

[0085] Among them, μ A (x) is the membership function, x is the input variable, c is the center of the membership function, a is the width parameter, and b is the shape parameter; by adjusting the c, a, and b parameters, fuzzy control of multiple variables in the crystallization process can be achieved.

[0086] This algorithm allows the system to achieve fuzzy control of multiple variables in the crystallization process by adjusting the c, a, and b parameters. For example, when controlling the crystallization temperature, the system sets c = 45°C (optimal crystallization temperature), a = 5°C (temperature fluctuation range), and b = 2 (control sensitivity). This way, when the temperature approaches 45°C, the system will adopt more moderate control measures; when the temperature deviates significantly, the system will adopt more aggressive control measures.

[0087] Then, the synchronous control computer group 32 of the application layer 3 adopts the synchronous control algorithm:

[0088]

[0089] in, is the phase adjustment value of the i-th device, K is the synchronization gain coefficient, is the reference phase, is the current phase of the i-th device, and ω0 is the system reference frequency. By dynamically adjusting the K value, precise synchronous control of multiple devices can be achieved.

[0090] This algorithm achieves precise synchronization of multiple devices by dynamically adjusting the K value. In practice, the system adjusts the K value according to the different crystallization stages. For example, in the early stages of crystallization, a larger K value (such as 0.8) is set to quickly achieve synchronization; during the stable crystallization period, a lower K value (such as 0.3) is used to avoid over-adjustment.

[0091] Next, the comprehensive evaluation method module 233 in the functional module 23 adopts a multi-objective optimization algorithm:

[0092] F(x)=w1·f1(x)+w2·f2(x)+…+w n ·f n (x)

[0093] Among them, F(x) is the comprehensive evaluation function, f i (x) is the i-th evaluation index function, w i is the weight of the i-th evaluation index (∑w i =1), x is the decision variable vector; by dynamically adjusting w i value, and realize adaptive optimization of different evaluation indicators.

[0094] This algorithm dynamically adjusts w i The system dynamically adjusts the weights of various indicators based on actual conditions to achieve the optimal overall effect.

[0095] Finally, the shared database 21 uses a data compression algorithm:

[0096]

[0097] Where C(D) is the compression ratio, H(D) is the entropy of data D, and L(D) is the original length of data D. By minimizing C(D), efficient storage and transmission of large amounts of crystallization process data can be achieved.

[0098] This algorithm minimizes C(D) to efficiently store and transmit large amounts of crystallization process data. In practice, the system sets a compression ratio threshold, such as 0.7. When the compression ratio falls below this threshold, the system automatically adjusts the compression parameters to ensure efficient data storage and rapid transmission.

[0099] The present invention also proposes an intelligent control method for prilocaine crystallization equipment based on the aforementioned system. This method first collects various parameter data during the prilocaine crystallization process using the data acquisition card 11 and temperature controller 12 of the data acquisition layer 1. This data is then transmitted to the shared database 21 of the data interaction layer 2 via RS232 and RS485 interfaces. Next, the data processing module 222 of the intelligent data interaction system 22 filters and performs wavelet transform processing on the data stored in the shared database 21.

[0100] The processed data is transmitted to the expert system call module 223, which uses a fuzzy logic control algorithm for decision analysis. The analysis results are then sent to the central control computer 31 in the application layer 3, which performs overall system planning and scheduling. Finally, the synchronous control computer cluster 32, following the scheduling instructions from the central control computer 31, uses the synchronous control algorithm to achieve coordinated control of multiple devices.

[0101] The method of the present invention also includes a control decision algorithm:

[0102] u(t)=K(t)·e(t)

[0103] Where u(t) is the control output, K(t) is the adaptive gain, and e(t) is the control error. K(t) is updated according to the following rule:

[0104]

[0105] Among them, γ is the learning rate and sign() is the sign function.

[0106] This algorithm achieves adaptive and precise control of the crystallization process by dynamically adjusting K(t). For example, in the early stages of crystallization, the system sets a larger γ value (such as 0.1) to quickly adjust the control parameters; while during the crystallization stabilization period, the γ value is lowered (such as 0.01) to avoid over-adjustment.

[0107] In addition, the present invention also adopts a temperature prediction control algorithm:

[0108]

[0109] Where T(t+Δt) is the predicted temperature after Δt time, T(t) is the current temperature, is the temperature change rate, is the temperature acceleration; by dynamically adjusting Δt, accurate prediction and control of the temperature change during the crystallization process can be achieved.

[0110] This algorithm accurately predicts and controls temperature changes during the crystallization process by dynamically adjusting Δt. In practice, the system adjusts Δt according to the different stages of crystallization. For example, in the early stages of crystallization, a smaller Δt value (e.g., 1 second) is used to achieve a faster response; during the stable crystallization phase, a larger Δt value (e.g., 5 seconds) is used to reduce control frequency and save energy.

[0111] Finally, the present invention also includes a load balancing algorithm and a distributed optimization algorithm. The load balancing algorithm is:

[0112] L i (t) = α i ·P i (t)+β i ·M i (t)+γ i ·N i (t)

[0113] Among them, L i (t) is the load index of the i-th equipment unit, P i (t) is the processor utilization, M i (t) is the memory utilization, N i (t) is the network utilization rate, α i , β i , γ i is the weight coefficient (α i +β i +γ i =1); by dynamically adjusting α i , β i , γ i Achieve optimal allocation of multi-device resources.

[0114] For example, in data processing intensive tasks, the system will increase α i In network communication intensive tasks, the system will increase γ i value.

[0115] The distributed optimization algorithm is:

[0116] minF(x)=∑f i (x i )

[0117] stg i (x i )≤0, i=1, 2, ..., n

[0118] h(x1, x2, ..., x n)=0

[0119] Among them, F(x) is the global objective function, f i (x i ) is the local objective function of the ith subsystem, g i (x i ) is a local constraint, h(x1, x2, ..., x n ) is the global coupling constraint.

[0120] This algorithm achieves global optimal control of the entire prilocaine crystallization system by iteratively solving the optimization problems of each subsystem and coordinating global coupling constraints. For example, the system uses factors such as crystallization rate, product purity, and energy consumption as objective functions for different subsystems, using this algorithm to find the optimal balance.

[0121] In summary, the intelligent control system and method for prilocaine crystallization equipment proposed in this invention achieves precise control of the prilocaine crystallization process through the synergistic effect of a multi-layered system architecture and multiple intelligent algorithms. This system not only adapts to different crystallization conditions but also enables coordinated control of multiple devices, significantly improving the production efficiency and quality of prilocaine.

[0122] In a preferred embodiment of the present invention, we conducted comprehensive testing of an intelligent control system for a prilocaine crystallization plant. This system utilizes the layered architecture proposed in this invention and multiple intelligent algorithms, including adaptive filtering, fuzzy logic control, and synchronous control. We tested a typical prilocaine production batch, setting the crystallization temperature at 45°C and the crystallization time at 6 hours.

[0123] For comparison, we also tested a traditional PID control system as a comparative example. This system uses a fixed-parameter PID controller and does not adopt the intelligent algorithm and hierarchical architecture proposed in this invention.

[0124] We focus on the following indicators: crystallization yield, product purity, energy consumption, crystallization time stability and system response time. The detection methods for these indicators are as follows:

[0125] 1. Crystallization yield: Determined by weighing method, accurate to 0.01g.

[0126] 2. Product purity: Determined by high performance liquid chromatography (HPLC), accurate to 0.1%.

[0127] 3. Energy consumption: The electricity consumption of the entire crystallization process is measured by a smart meter with an accuracy of 0.1kWh.

[0128] 4. Crystallization time stability: Calculate the standard deviation of crystallization completion time in multiple experiments to the nearest 0.1 minute.

[0129] 5. System response time: Measures the time from when a temperature deviation is detected to when the system makes an adjustment, accurate to 0.1 second.

[0130] The following are the test results of Examples and Comparative Examples:

[0131]

[0132]

[0133] The test results show that the intelligent control system of the present invention is significantly superior to the traditional PID control system in all indicators. Let's analyze these results in depth:

[0134] First, the crystallization yield increased by 3.5 percentage points, a significant improvement. In industrial production, this means more product can be produced from the same raw materials, significantly improving production efficiency. This improvement is primarily due to the precise temperature control and multi-objective optimization algorithm of the present invention, which maintain optimal crystallization conditions throughout the entire crystallization process.

[0135] Secondly, product purity has also been significantly improved, from 98.9% to 99.7%. While this difference may seem only 0.8 percentage points, it represents a significant advancement in the production of high-purity products. Higher purity translates to improved product quality, potentially opening up new applications or meeting the demands of higher-end markets. This is primarily due to the fuzzy logic control algorithm of the present invention, which enables more precise control of various parameters during the crystallization process.

[0136] In terms of energy consumption, the system of the present invention saves 14.2% compared to traditional systems. This not only reduces production costs but also aligns with current trends in energy conservation and emission reduction. This energy saving is primarily due to the load balancing algorithm and distributed optimization algorithm of the present invention, which more rationally allocate and utilize system resources.

[0137] The improvement in crystallization time stability is also significant. The crystallization time fluctuation of the system of the present invention is only ±2.3 minutes, while the traditional system is as high as ±7.8 minutes. This means that the system of the present invention can provide a more stable and predictable production process, which is conducive to the formulation and execution of production plans. This is mainly due to the synchronous control algorithm and temperature prediction control algorithm of the present invention.

[0138] Finally, the system response time was reduced from 2.1 seconds to 0.5 seconds, a 76.2% improvement. This faster response time means the system can react more quickly to process fluctuations, thereby maintaining a more stable crystallization environment. This is primarily due to the adaptive control algorithm and layered architecture design of the present invention.

[0139] Overall, these test results fully demonstrate the superiority of the system of the present invention. It not only improves product quantity and quality, but also reduces energy consumption, improves production stability, and enhances system response speed. These improvements will bring significant economic benefits and quality improvements to the production of prilocaine.

[0140] It’s worth noting that while this test was conducted under specific conditions, the adaptability and intelligence of the proposed system means it can maintain this advantage under a wider range of conditions. In the future, we can consider conducting more tests under different temperature ranges, batch sizes, and other conditions to further verify the adaptability and stability of the proposed system.

[0141] It should be noted that the above is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. Intelligent control system of prilocaine crystallization equipment, characterized in that: The system includes data collection layer, data interaction layer and application layer, among which: The data acquisition layer includes multiple data acquisition cards and temperature controllers. The data acquisition cards are used to collect temperature, liquid level, and dissolved oxygen parameters during the crystallization of prilocaine, and feed the collected process data back to the computer through the RS232 interface; the temperature controller receives the control signal of the computer through the RS485 interface, and is used to control the temperature of each crystallization device. At the same time, the crystallization device and process parameters are collected and sent to the shared database of the data interaction layer; The data interaction layer includes a shared database, an intelligent data interaction system and a functional module, wherein the shared database is used to store and manage the collected process data and control instructions; the intelligent data interaction system includes a data acquisition module, a data processing module and an expert system call module, the data acquisition module is responsible for acquiring data from the shared database, the data processing module performs filtering and wavelet transform processing on the data, and the expert system call module is responsible for decision analysis; the functional module includes a prilocaine crystallization process module, an evaluation criterion module and a comprehensive evaluation method module, which are used to provide crystallization process knowledge, evaluation indicators and optimization methods; The application layer includes a central control computer and a synchronous control computer group. The central control computer is responsible for the planning and scheduling of the overall system, rationally allocates various resources of the system, and can perform manual control. The synchronous control computer group is responsible for executing intelligent control application strategies and independently controlling the crystallization equipment through a shared database.

2. The prilocaine crystallization equipment intelligent control system according to claim 1, characterized in that: The data acquisition card of the data acquisition layer adopts the following data filtering algorithm: Y(n)=α·X(n)+(1-α)·Y(n-1) Among them, Y(n) is the current filtered data, X(n) is the current collected original data, Y(n-1) is the data after the last filtering, and α is the filter coefficient (0<α<1); by dynamically adjusting the α value, adaptive filtering for different noise levels can be achieved.

3. The intelligent control system for prilocaine crystallization equipment according to claim 1, characterized in that: The expert system call module of the data interaction layer adopts the following fuzzy logic control algorithm: Among them, μ A (x) is the membership function, x is the input variable, c is the center of the membership function, a is the width parameter, and b is the shape parameter; by adjusting the c, a, and b parameters, fuzzy control of multiple variables in the crystallization process can be achieved.

4. The intelligent control system for prilocaine crystallization equipment according to claim 1, characterized in that: The synchronous control computer group of the application layer adopts the following synchronous control algorithm: in, is the phase adjustment of the i-th device, K is the synchronization gain coefficient, is the reference phase, is the current phase of the i-th device, and ω0 is the system reference frequency. By dynamically adjusting the K value, precise synchronous control of multiple devices can be achieved.

5. The intelligent control system for prilocaine crystallization equipment according to claim 1, characterized in that: The comprehensive evaluation method module in the functional module adopts the following multi-objective optimization algorithm: F(x)=w1·f1(x)+w2·f2(x)+…+w n ·f n (x) Among them, F(x) is the comprehensive evaluation function, f i (x) is the i-th evaluation index function, w i is the weight of the i-th evaluation index (∑w i =1), x is the decision variable vector; by dynamically adjusting w i value to achieve adaptive optimization of different evaluation indicators.

6. The intelligent control system for prilocaine crystallization equipment according to claim 1, characterized in that: The shared database uses the following data compression algorithm: Among them, C(D) is the compression rate, H(D) is the entropy of data D, and L(D) is the original length of data D. By minimizing C(D), efficient storage and transmission of a large amount of crystallization process data can be achieved.

7. An intelligent control method for prilocaine crystallization equipment based on the system according to any one of claims 1 to 6, characterized in that: The method comprises the following steps: Firstly, the temperature, liquid level and dissolved oxygen parameter data of the prilocaine crystallization process are collected through the data acquisition card and temperature controller of the data acquisition layer; Next, the collected data is transmitted to the shared database of the data exchange layer through RS232 and RS485 interfaces; Then, the data processing module of the intelligent data interaction system performs filtering and wavelet transformation on the data stored in the shared database; Subsequently, the processed data are transmitted to the expert system call module, which performs decision analysis using fuzzy logic control algorithm; Next, the analysis results are sent to the central control computer at the application layer, which performs the planning and scheduling of the overall system; Finally, the synchronous control computer group uses the synchronous control algorithm to achieve coordinated control of multiple devices according to the scheduling instructions of the central control computer.

8. The intelligent control method for prilocaine crystallization equipment according to claim 7, characterized in that: The method also includes the following control decision algorithm: u(t)=K(t)·e(t) Where u(t) is the control output, K(t) is the adaptive gain, and e(t) is the control error. K(t) is updated by the following rule: Among them, γ is the learning rate and sign() is the sign function; by dynamically adjusting K(t), adaptive and precise control of the crystallization process can be achieved.

9. The intelligent control method for prilocaine crystallization equipment according to claim 7, characterized in that: The method also includes the following temperature prediction control algorithm: Where T(t+Δt) is the predicted temperature after Δt time, T(t) is the current temperature, is the temperature change rate, is the temperature acceleration; by dynamically adjusting Δt, accurate prediction and control of the temperature change in the crystallization process can be achieved.

10. The intelligent control method for prilocaine crystallization equipment according to claim 7, characterized in that: The method also includes the following load balancing algorithm and distributed optimization algorithm: L i (t)=a i ·P i (t)+β i ·M i (t)+γ i ·N i (t) Among them, L i (t) is the load index of the i-th equipment unit, P i (t) is the processor utilization, M i (t) is the memory utilization, N i (t) is the network utilization, α i , β i , γ i is the weight coefficient (α i +β i +γ i =1); by dynamically adjusting α i , β i , γ i Achieve optimal allocation of multi-device resources; Distributed optimization algorithm: minF(x)=∑f i (x i ) s.t.g i (x i )≤0,i=1,2,...,n h(x1,x2,...,x n )=0 Among them, F(x) is the global objective function, f i (x i ) is the local objective function of the ith subsystem, g i (x i ) is a local constraint, h(x1, x2, ..., x n ) is the global coupling constraint; by iteratively solving the optimization problems of each subsystem and coordinating the global coupling constraints, the global optimization control of the entire prilocaine crystallization system is achieved.

Images