Intelligent monitoring method and system for fumigation liquid production

Abstract

The invention relates to the technical field of computers, and discloses an intelligent monitoring method and system for fumigation liquid production, and the method comprises the steps: collecting energy consumption data in a fumigation liquid production process in real time through a sensor, and uploading the energy consumption data to a block chain; verifying the legality of the uploaded data, and when the data is verified to be legal, triggering an intelligent contract to execute an optimization decision, and automatically adjusting the operation parameters of the fumigation liquid; and an adjustment result is fed back through the block chain, and the intelligent contract is iterated according to real-time data, so that continuous improvement of the system is ensured. Through combination of the Lagrange programming neural network and the simulated annealing algorithm, multi-stage constraints can be effectively processed, it is ensured that key parameters in the production process are accurately controlled, and the production efficiency is improved. Through a continuous feedback mechanism and optimization iteration, it is ensured that energy consumption in the fumigation liquid production process is always in an optimal state, and dual optimization of energy saving and production benefits is achieved.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to an intelligent monitoring method and system for fumigant liquid production. Background Art

[0002] The fumigant production process typically involves multiple key steps, such as heating, ventilation, and humidity control. The energy consumption of each step directly impacts production efficiency and energy costs. Traditional production control methods typically rely on manual operation or automated control systems based on preset rules. These systems often suffer from several issues. First, they are unable to adjust various parameters during the production process in real time. This is particularly true when anomalies occur during the production process or when the external environment changes, making it difficult for traditional control methods to respond quickly. Second, the lack of transparency and traceability of production process data hinders the effectiveness of data analysis and optimized decision-making.

[0003] Currently, blockchain-based smart contracts and data-driven optimization and control methods have become important approaches for improving production efficiency and reducing energy consumption. The emergence of blockchain technology provides technical guarantees for data transparency, security, and immutability, while smart contracts enable automated decision-making and execution, reducing human intervention and improving system automation. In industrial production, an increasing number of applications are relying on blockchain technology for data storage and management, ensuring the integrity and reliability of production data. However, despite the significant advantages of blockchain technology and smart contracts in improving system transparency and efficiency, existing technologies still face challenges such as real-time data processing and multi-constraint optimization decision-making.

[0004] To address these challenges, the application of artificial intelligence (AI), particularly deep learning and optimization algorithms, in industrial control systems has been gaining momentum in recent years. By combining neural networks with traditional optimization algorithms, they can better handle multivariable and multi-constrained optimization problems in complex production processes, enhancing the intelligence of the system. However, existing AI-based optimization methods often rely on static models or simple constraints, lacking the flexibility to adapt to real-time data and struggling to handle optimization problems with multiple levels of constraints and complex production environments.

[0005] Therefore, how to combine blockchain technology and smart contracts, use advanced optimization algorithms (such as Lagrangian programming neural networks, simulated annealing algorithms, etc.) to process multi-level constraints in real time and dynamically adjust operating parameters has become a technical problem that needs to be solved urgently. Summary of the Invention

[0006] In view of the above-mentioned problems, the present invention is proposed.

[0007] Therefore, the technical problems solved by the present invention are: energy consumption optimization, multi-level constraint processing and real-time adjustment of operating parameters in the fumigant liquid production process.

[0008] To solve the above technical problems, the present invention provides the following technical solutions: an intelligent monitoring method for fumigant production, comprising: collecting energy consumption data during fumigant production in real time through sensors and uploading it to a blockchain; Verify the legitimacy of the uploaded data. When the data is verified to be legitimate, the smart contract is triggered to execute the optimization decision and automatically adjust the operating parameters of the fumigant liquid; Adjust results through blockchain feedback and iterate smart contracts based on real-time data to ensure continuous system improvement; The smart contract includes using an improved Lagrangian programming neural network to process the constraints in the fumigant liquid production process and preliminarily optimize the operating parameters; using a simulated annealing algorithm to conduct a global search of the operating parameters to obtain the optimal operating parameters for the fumigant liquid.

[0009] As a preferred embodiment of the intelligent monitoring method for fumigant production according to the present invention, the energy consumption data includes temperature data, humidity data, air flow velocity, heating power, equipment load data, production time, evaporation rate and energy efficiency data; The uploading of the energy consumption data to the blockchain includes: attaching a timestamp and a device identifier to each piece of the energy consumption data, and transmitting the data to the blockchain via wireless communication for storage.

[0010] As a preferred embodiment of the intelligent monitoring method for fumigant production according to the present invention, the verification of the legitimacy of the uploaded data includes: the smart contract receives energy consumption data with a timestamp and device identification from the blockchain, and performs data rationality verification, consistency verification, and time verification; The data rationality verification is to determine whether the energy consumption data meets the preset data standards; the consistency verification is to check whether there are abnormal fluctuations in the data collected by different sensors; the time verification is to verify whether the timestamp of the energy consumption data is reasonable; When the energy consumption data uploaded to the blockchain meets all verification conditions, the smart contract confirms the data is legitimate and triggers the smart contract to execute the optimization decision; When the energy consumption data uploaded to the blockchain does not meet all verification conditions, the smart contract records the abnormal data and triggers an alarm to notify the operator.

[0011] As a preferred embodiment of the intelligent monitoring method for fumigant production described in the present invention, the improved Lagrangian programming neural network introduces a multi-level constraint mechanism and optimizes the constraint conditions in the fumigant production process through the Lagrangian multiplier method; by setting the Lagrangian multipliers of the primary, secondary, and tertiary constraints, the influence of each constraint on the objective function is weightedly controlled, thereby preliminarily optimizing the operating parameters in the fumigant production process; The improved Lagrangian programming neural network includes an input layer, a hidden layer and an output layer; The input layer receives legal energy consumption data; Hidden layer: consists of three layers of neural network, each layer includes 32 neurons; The first hidden layer: receives input layer data, performs preliminary feature extraction, learns the correlation in the input data; uses the ReLU activation function to perform nonlinear mapping on the data; The second hidden layer receives the data output by the first layer, further extracts features, and uses the ReLU activation function for nonlinear mapping; The third hidden layer: receives the features output by the first two layers, performs feature concatenation and optimization, and passes them to the output layer; Output layer: Output preliminary optimized operating parameters, including heating temperature, air flow rate, humidity control, equipment load, production time, evaporation rate, equipment power and cooling temperature and speed.

[0012] As a preferred embodiment of the intelligent monitoring method for fumigant production according to the present invention, the multi-level constraint mechanism includes primary constraint, secondary constraint and tertiary constraint; Each constraint is introduced into the objective function through Lagrange multipliers, where , represents the Lagrange multiplier of the first-order constraint; Lagrange multipliers representing secondary constraints; Lagrange multipliers representing the three-level constraints; The objective function is to minimize energy consumption; The loss function is composed of the objective function and the penalty term of the constraint condition. The penalty term of each constraint condition is multiplied by the corresponding Lagrange multiplier, and the influence of the constraint on the optimization objective is controlled by weighting.

[0013] As a preferred embodiment of the intelligent monitoring method for fumigant liquid production of the present invention, the global search for the preliminary optimized operating parameters using the simulated annealing algorithm includes: using the preliminary optimized operating parameters as the initial solution of the simulated annealing algorithm; setting an initial temperature value, and gradually reducing the temperature as the iteration proceeds; generating new candidate solutions by slightly perturbing the initial solution, and performing multiple rounds of iterations; Calculate the energy consumption difference between the current solution and the new solution. When the energy consumption of the new candidate solution is lower than that of the current solution, accept the new solution unconditionally. When the energy consumption of the new candidate solution is higher than that of the current solution, decide whether to accept the new solution based on the acceptance probability. When the temperature drops to the set low value or reaches the maximum number of iterations, the search stops and the optimal operating parameters of the fumigant liquid are output.

[0014] As a preferred embodiment of the intelligent monitoring method for fumigant liquid production described in the present invention, the iterative smart contract based on real-time data includes: the optimal operating parameters are fed back to the system via the blockchain as input for the next round of smart contract optimization.

[0015] Intelligent monitoring system for fumigant production, including: The data module collects energy consumption data during the fumigation liquid production process in real time through sensors and uploads it to the blockchain; The blockchain module verifies the legitimacy of the uploaded data. When the data is verified to be legitimate, it triggers the smart contract to execute optimization decisions and automatically adjust the operating parameters of the fumigant liquid; The iteration module adjusts the results through blockchain feedback and iterates the smart contract based on real-time data to ensure continuous improvement of the system.

[0016] A computer device comprises: a memory and a processor; the memory stores a computer program, wherein the processor implements the steps of any one of the methods of the present invention when executing the computer program.

[0017] A computer-readable storage medium stores a computer program thereon, wherein the computer program, when executed by a processor, implements the steps of any one of the methods of the present invention.

[0018] Beneficial effects of the present invention: The intelligent monitoring method for fumigant production provided by the present invention ensures data transparency and immutability by collecting and uploading energy consumption data to the blockchain in real time, thereby improving data reliability. Smart contracts automatically trigger optimization decisions based on verified legal data, adjusting operating parameters in the fumigant production process in real time, optimizing energy consumption, and reducing manual intervention. The combination of a Lagrangian programming neural network and a simulated annealing algorithm effectively handles multi-level constraints, ensuring precise control of key parameters in the production process and improving production efficiency. Through continuous feedback mechanisms and optimization iterations, energy consumption in the fumigant production process is ensured to be consistently optimal, achieving dual optimization of energy conservation and production efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0020] Figure 1 This is an overall flow chart of the intelligent monitoring method for fumigant liquid production provided by the first embodiment of the present invention. DETAILED DESCRIPTION

[0021] To make the above-mentioned objects, features, and advantages of the present invention more clearly understood, the following detailed description of the specific embodiments of the present invention is given in conjunction with the accompanying drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in this field without creative work should fall within the scope of protection of the present invention.

[0022] Example 1, with reference to Figure 1 , as one embodiment of the present invention, provides an intelligent monitoring method for fumigant liquid production, comprising: S1: Energy consumption data during the fumigation liquid production process is collected in real time through sensors and uploaded to the blockchain.

[0023] Energy consumption data includes temperature data, humidity data, air flow velocity, heating power, equipment load data, production time, evaporation rate and energy efficiency data.

[0024] Sensors are installed at key stages of the fumigant production process (heating, ventilation, and humidity control) to collect real-time data on energy consumption. These sensors continuously monitor and update data every minute to ensure data is up-to-date.

[0025] The collected energy consumption data is transmitted to the blockchain network via wireless communication (such as LoRa, NB-IoT, etc.).

[0026] Energy consumption data is stored on the blockchain, and each piece of energy consumption data is accompanied by a timestamp and device identification to ensure the data is tamper-proof and transparent.

[0027] By collecting energy consumption data in real time and uploading it to the blockchain, all critical data from the fumigant production process is accurately recorded, transparently stored, and tamper-proof. Sensors installed at key stages such as heating, ventilation, and humidity control continuously monitor energy consumption data such as temperature, humidity, airflow velocity, heating power, and equipment load, updating them every minute to ensure data timeliness and accuracy. Leveraging wireless communication technologies (such as LoRa and NB-IoT), collected data is transmitted to the blockchain network in real time. This not only provides an efficient data transmission mechanism but also ensures the immutability and transparency of all data, providing a reliable foundation for subsequent smart contract optimization and decision-making. This design also provides strong guarantees for data security and quality control during the production process, avoiding the potential for data leakage or tampering associated with traditional methods and improving traceability and compliance in the production process.

[0028] S2: Verify the legitimacy of the uploaded data. When the data is verified to be legitimate, the smart contract is triggered to execute the optimization decision and automatically adjust the operating parameters of the fumigant.

[0029] The smart contract receives the uploaded energy consumption data from the blockchain and performs legitimacy verification including: Data rationality verification: According to the predetermined standards, the temperature should be between 18°C ​​and 22°C, and the humidity should be between 50% and 60%. Check whether the temperature and humidity in the data are within the specified range; and verify whether the equipment load and power data are within the allowable operating range of the equipment.

[0030] Consistency Verification: This checks the consistency of data from different sensors to ensure that parameters such as temperature, humidity, and airflow do not fluctuate abnormally, avoiding data errors caused by sensor failure. If energy consumption data fluctuations within a certain period exceed m times the standard deviation, the data for that period is considered abnormal.

[0031] Time verification: The smart contract verifies whether the timestamp of the data is reasonable and ensures that each piece of data is accompanied by a device identifier to prevent data forgery or tampering.

[0032] When the uploaded data meets all verification conditions, the smart contract confirms the legitimacy of the data and triggers subsequent optimization decisions.

[0033] When the data does not meet all verification conditions, the smart contract will record the abnormal data and trigger an alarm to prevent erroneous data from affecting subsequent decisions.

[0034] The smart contract includes using an improved Lagrangian programming neural network to process the constraints in the fumigant production process and optimize the energy consumption in the fumigant production process; using a simulated annealing algorithm to perform a global search for operating parameters, and combining the Newton method to perform local optimization of the global search results to obtain the optimal operating parameters of the fumigant.

[0035] Operating parameters include heating temperature, air flow rate, humidity control, equipment load, production time, evaporation rate, equipment power, and cooling temperature and rate.

[0036] Heating temperature: This controls the temperature parameters during the fumigant production process. Temperature affects evaporation rate and energy consumption. Proper temperature setting ensures production efficiency and energy optimization.

[0037] Airflow velocity: In the fumigant production process, the airflow velocity has an important influence on heating and humidity control.

[0038] Humidity control: Control the humidity of the fumigant production environment to ensure that the humidity remains within the specified range.

[0039] Equipment load: Equipment load refers to the workload of the equipment (heaters, ventilators, pumps), which affects energy consumption and the operating efficiency of the equipment.

[0040] Production time: The duration of the production process, i.e. the time required to produce each batch. The longer the production time, the higher the energy consumption is likely to be.

[0041] Evaporation rate: The rate at which liquid evaporates during production, which is typically closely related to temperature, airflow, and humidity. By controlling the evaporation rate, energy consumption can be optimized and product quality can be controlled.

[0042] Equipment Power: Controls the power output of each production equipment (heaters, fans, pumps). Proper power distribution improves energy efficiency and avoids equipment overload or inefficient operation.

[0043] An improved Lagrangian programming neural network introduces a multi-level constraint mechanism and uses the Lagrangian multiplier method to optimize the constraints in the fumigant production process. By adjusting the Lagrangian multipliers for the primary, secondary, and tertiary constraints and dynamically weighting their impact on the objective function, the operating parameters in the fumigant production process are initially optimized.

[0044] The Lagrangian programming neural network consists of an input layer, a hidden layer, and an output layer.

[0045] Input layer: receives valid energy consumption data and consists of 6 neurons.

[0046] There are 3 hidden layers, with 32 neurons in each layer.

[0047] First Hidden Layer: Data received from the input layer enters the first hidden layer, where it performs preliminary feature extraction and learns correlations within the input data. The ReLU activation function is used to apply a nonlinear mapping to the data, allowing the model to learn complex patterns. The output of the first hidden layer is a nonlinear transformation of the original features, which are further processed and optimized in subsequent layers.

[0048] Second hidden layer: The second layer further learns more complex patterns and features from the data output by the first layer. The ReLU activation function is used to nonlinearly map the data, ensuring that the network can learn nonlinear relationships. The output of the second layer is an optimization and transformation of the results of the previous layer, aiming to strengthen the connections between the data.

[0049] The third hidden layer: The third layer further concatenates the features output by the first two layers, maintains nonlinear feature learning through the ReLU activation function, generates optimized feature representations, and finally passes them to the output layer.

[0050] Output layer: Generates and outputs the optimized preliminary operation parameters.

[0051] In the training of LPNN, in order to better control the fumigation liquid production process, a multi-level constraint mechanism is introduced. The constraints are divided into three levels: Level 1 constraints (critical constraints): These constraints directly impact product quality and production process safety and must be strictly controlled. These include: Heating temperature: Maintained within a set range to ensure production efficiency and product quality. Humidity control: Humidity should be within empirically defined limits to avoid affecting evaporation rates and product quality. Equipment load: Equipment load must remain within a safe operating range to prevent overload.

[0052] Secondary constraints (optimization constraints): These constraints affect production efficiency and system stability, but have a less direct impact on product quality than primary constraints. These constraints include: Production rate: Controlled within a fixed hourly fumigant demand to ensure efficient production. Concentrate volume: The final concentrate volume should remain within a set range to ensure process stability.

[0053] Level 3 constraints (sustainability constraints): These constraints have a smaller direct impact on production but may affect costs and sustainability in the long term. These constraints include: Ambient temperature fluctuation: This should be controlled between 20°C and 35°C to avoid drastic fluctuations that can indirectly impact production efficiency. Water quality: Purified water should be used to ensure that the water quality meets fumigant production standards.

[0054] Each constraint is introduced into the optimization objective function through the Lagrange multiplier method. Each constraint corresponds to a Lagrange multiplier. , the size of the multiplier determines the degree of influence of the constraint on the optimization of the objective function. The Lagrange multiplier formula is expressed as: ; in, are the first-order constrained Lagrange multipliers, which dominate the objective function optimization process and ensure that the production process is carried out under strict control. Lagrange multipliers representing the secondary constraints; although secondary constraints are not as strict as primary constraints, they still need to be optimized during training. The Lagrange multiplier representing the third-level constraint has the smallest impact on the objective function, typically related to cost and sustainability. To avoid overconstraining the fumigant production process, the third-level constraint's Lagrange multiplier is minimized. The Lagrange multiplier for the first-level constraint is over 10 times larger than the second-level constraint, and the second-level constraint's Lagrange multiplier is over 50 times larger than the third-level constraint.

[0055] The loss function consists of the objective function (minimizing energy consumption) and the penalty term of the constraint condition. The penalty term of each constraint condition is multiplied by the corresponding Lagrange multiplier, and the influence of the constraint on the optimization objective is controlled by weighting. The formula is: ; in, represents the objective function of minimizing energy consumption. represents the penalty term of the j-th constraint, It is the Lagrange multiplier of the jth constraint, and its size is dynamically adjusted to control the impact of the constraint on the optimization objective. represents the Lagrangian function, and j represents the index.

[0056] The training objective of the Lagrangian programming neural network is to minimize the loss function while ensuring that all constraints are met. The training process involves feeding energy consumption data into the Lagrangian programming neural network through the input layer, performing feature learning and constraint processing in the hidden layer, and finally calculating the optimal operating parameters through the output layer.

[0057] The loss function is calculated using the backpropagation algorithm and minimized using gradient descent, ensuring that the constraints are satisfied. The Lagrange multiplier is dynamically adjusted based on the actual impact of each constraint, ensuring a balance between the objective function and the constraints during the optimization process.

[0058] The initial optimized operating parameters are used as the initial solution for simulated annealing; an initial temperature value is set. , initial temperature Determines the degree of exploration during the algorithm's search. A higher initial temperature makes the algorithm more receptive to poor solutions, helping it search a wider range of solutions. As iterations proceed, the temperature gradually decreases.

[0059] The temperature will gradually decrease, and as the temperature decreases, the search pace will become more refined, avoiding large-scale searches and ensuring that the algorithm can stabilize near the global optimal solution.

[0060] The simulated annealing algorithm generates new candidate solutions by making small perturbations to the initial solution and iterates over multiple rounds. The difference in energy consumption ΔE between the current solution and the new solution is calculated using the formula: ; in, is the new solution of energy consumption, is the energy consumption of the current solution.

[0061] When the energy consumption of the new solution is lower than that of the current solution ( ), the new solution is accepted unconditionally; when the energy consumption of the new solution is higher than the current solution ( ), then the decision on whether to accept the new solution is based on the acceptance probability. The formula for the probability of accepting the new solution is expressed as: ; in, represents the probability of accepting the new solution, Indicates the current temperature.

[0062] Generate a random number , which is a random number between [0,1]; when Then accept the new interpretation.

[0063] when , the new solution is rejected and the current solution is kept.

[0064] As the search progresses, the temperature will gradually decay, reducing the probability of accepting a poor solution and gradually converging to a stable solution. The formula for temperature decay is usually: ; in, It is a constant less than 1 that determines the temperature decay rate. Indicates the temperature in the new iteration; Indicates the temperature in the current iteration.

[0065] When the temperature drops to the set low value, the algorithm stops; when the annealing algorithm reaches the maximum number of iterations, the search stops and the optimal operating parameters are obtained.

[0066] Furthermore, the simulated annealing algorithm plays a significant role in optimizing operating parameters (such as heating temperature, airflow rate, humidity control, and equipment load) during the fumigant production process. Through global search, simulated annealing effectively avoids the local optimal solution issues that can occur with traditional optimization methods, ensuring that parameter optimization reaches the global optimal solution. This process, achieved through dynamic temperature control, not only explores a broad solution space but also ensures that the final operating parameters meet the strict constraints of the production process (such as heating temperature and humidity control). Simulated annealing provides an efficient and robust solution to complex multi-parameter optimization problems, minimizing energy consumption and maximizing production efficiency during the production process.

[0067] Furthermore, the benefit of using a simulated annealing algorithm lies in its ability to explore a wide range of parameter spaces, avoiding the common problem of relying solely on local search. By setting an initial temperature value, the algorithm can accept less favorable solutions during the search process, thereby escaping the local optimum and gradually finding the global optimal solution. As the temperature gradually decreases, the algorithm converges to the optimal solution, ensuring that the operating parameters in the production process have the highest energy efficiency and production stability. In this way, key operating parameters such as temperature, humidity, and equipment load in the fumigant production process can be precisely optimized to ensure the efficiency and sustainability of the production process.

[0068] Furthermore, the constraints in the fumigant production process were addressed using a Lagrangian programming neural network (LPNN). These constraints were then incorporated into the optimization objective function as penalty terms, ensuring optimization while avoiding violations of key production constraints (such as temperature, humidity, and equipment load). The simulated annealing algorithm, used as a global search tool, further ensured that the optimal solution could be found globally, avoiding the problem of local optimal solutions.

[0069] Based on simulated annealing, a multi-level constraint mechanism is incorporated. By dynamically adjusting the size of the Lagrange multiplier, the constraints at different levels are properly controlled. For example, primary constraints (such as temperature and humidity) have a significant impact on the optimization process, secondary constraints (such as production rate and concentrate volume) have a smaller but significant impact, and tertiary constraints (such as ambient temperature fluctuations and water quality) focus more on production sustainability. This hierarchical constraint approach ensures that the optimization process not only focuses on minimizing energy consumption but also takes into account the safety, stability, and long-term sustainability of the production process.

[0070] The simulated annealing algorithm's global search capability ensures that it can escape local optima in complex optimization problems and find globally optimal operating parameters, thereby ensuring optimal production processes. Multi-level constraints are introduced into the objective function using the Lagrange multiplier method, and their weight in the optimization process is dynamically adjusted based on their actual impact, ensuring that each constraint is appropriately considered. This flexible constraint handling approach effectively balances minimizing energy consumption with the safety and stability of the production process. As the temperature gradually decreases, the simulated annealing algorithm not only reduces randomness in the search process but also allows for fine-tuning of parameters to ensure the ultimate optimal operating parameters. This gradual cooling process enhances the stability and accuracy of the optimization results. By precisely optimizing the operating parameters, energy consumption is effectively reduced while ensuring production efficiency, thereby improving the sustainability of production.

[0071] S3: Adjust results through blockchain feedback and iterate smart contracts based on real-time data to ensure continuous system improvement; The final optimized operating parameters are returned to the system via the blockchain. Each adjusted operating parameter is monitored throughout the production process, with real-time data continuously uploaded to the blockchain for verification. Based on this new real-time data, the smart contract will continue to make optimization adjustments, ensuring continuous improvement at every step of the production process.

[0072] Smart contracts validate the effectiveness of each adjustment based on real-time data fed back from the blockchain and trigger new optimization decisions to ensure operating parameters are always optimal. Through continuous data updates and feedback, smart contracts continuously adjust operating parameters to address potential changes in the production process, ensuring long-term system optimization.

[0073] Each optimized and adjusted operating parameter is fed back into the system as input for the next round of optimization, forming a closed-loop feedback mechanism. By recording each optimization result on the blockchain, the system can continuously optimize according to changing production conditions, ensuring optimal energy consumption at every production run.

[0074] Furthermore, the use of smart contracts, blockchain, and real-time data feedback significantly improves traditional fumigant production control methods. Traditional methods rely on manually set, fixed control parameters, are unable to dynamically adjust to changes in production, and lack transparency and data traceability. This new method, however, collects real-time energy consumption data from the production process, uploads it to the blockchain, verifies the data's legitimacy, and automatically triggers optimization decisions. Using smart contracts to adjust production parameters, it improves the flexibility and efficiency of the production process.

[0075] Furthermore, by recording every operational parameter adjustment on a blockchain, this invention enhances the transparency and traceability of the production process, meeting industry requirements for data security and compliance. Compared to traditional methods, this invention not only optimizes energy consumption and production efficiency, but also enables continuous system improvement, avoiding errors caused by human intervention, thereby providing more reliable and efficient production process management.

[0076] Example 2, an embodiment of the present invention, provides an intelligent monitoring system for fumigant liquid production, comprising: The data module collects energy consumption data during the fumigation liquid production process in real time through sensors and uploads it to the blockchain.

[0077] The blockchain module verifies the legitimacy of the uploaded data. When the data is verified to be legitimate, it triggers the smart contract to execute optimization decisions and automatically adjust the operating parameters of the fumigant liquid.

[0078] The iteration module adjusts the results through blockchain feedback and iterates the smart contract based on real-time data to ensure continuous improvement of the system.

[0079] If the above functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or the portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes various media that can store program code, such as USB flash drives, mobile hard drives, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical disks.

[0080] The logic and / or steps represented in a flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can retrieve and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0081] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically by optically scanning the paper or other medium, then editing, deciphering, or processing in another suitable manner as necessary, and then storing it in a computer memory.

[0082] It should be understood that various components of the present invention may be implemented using hardware, software, firmware, or a combination thereof. In the aforementioned embodiments, multiple steps or methods may be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one or combination of the following technologies known in the art may be used: a discrete logic circuit having logic gate circuits for implementing logic functions on data signals, an application-specific integrated circuit having suitable combinational logic gate circuits, a programmable gate array (PGA), a field-programmable gate array (FPGA), etc.

[0083] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. An intelligent monitoring method for fumigant liquid production, characterized in that: include: Energy consumption data during fumigation production is collected in real time through sensors and uploaded to the blockchain; Verify the legitimacy of the uploaded data. When the data is verified to be legitimate, the smart contract is triggered to execute the optimization decision and automatically adjust the operating parameters of the fumigant liquid; Adjust results through blockchain feedback and iterate smart contracts based on real-time data to ensure continuous system improvement; The smart contract includes using an improved Lagrangian programming neural network to process the constraints in the fumigant liquid production process and preliminarily optimize the operating parameters; using a simulated annealing algorithm to conduct a global search of the operating parameters to obtain the optimal operating parameters for the fumigant liquid.

2. The intelligent monitoring method for fumigant production according to claim 1, wherein: The energy consumption data includes temperature data, humidity data, air flow velocity, heating power, equipment load data, production time, evaporation rate and energy efficiency data; The uploading of the energy consumption data to the blockchain includes: attaching a timestamp and a device identifier to each piece of the energy consumption data, and transmitting the data to the blockchain via wireless communication for storage.

3. The intelligent monitoring method for fumigant production according to claim 2, wherein: Verifying the legitimacy of uploaded data includes: the smart contract receives energy consumption data with timestamps and device identifiers from the blockchain, and performs data rationality verification, consistency verification, and time verification; The data rationality verification is to determine whether the energy consumption data meets the preset data standards; the consistency verification is to check whether there are abnormal fluctuations in the data collected by different sensors; the time verification is to verify whether the timestamp of the energy consumption data is reasonable; When the energy consumption data uploaded to the blockchain meets all verification conditions, the smart contract confirms the data is legitimate and triggers the smart contract to execute the optimization decision; When the energy consumption data uploaded to the blockchain does not meet all verification conditions, the smart contract records the abnormal data and triggers an alarm to notify the operator.

4. The intelligent monitoring method for fumigant liquid production according to claim 3, characterized in that: The improved Lagrangian programming neural network introduces a multi-level constraint mechanism and optimizes the constraint conditions in the fumigant production process through the Lagrangian multiplier method; by setting the Lagrangian multipliers of the first, second and third level constraints, the influence of each constraint on the objective function is weightedly controlled, thereby preliminarily optimizing the operating parameters in the fumigant production process; The improved Lagrangian programming neural network includes an input layer, a hidden layer and an output layer; The input layer receives legal energy consumption data; Hidden layer: consists of three layers of neural network, each layer includes 32 neurons; The first hidden layer: receives input layer data, performs preliminary feature extraction, learns the correlation in the input data; uses the ReLU activation function to perform nonlinear mapping on the data; The second hidden layer receives the data output by the first layer, further extracts features, and uses the ReLU activation function for nonlinear mapping; The third hidden layer: receives the features output by the first two layers, performs feature concatenation and optimization, and passes them to the output layer; Output layer: Output preliminary optimized operating parameters, including heating temperature, air flow rate, humidity control, equipment load, production time, evaporation rate, equipment power and cooling temperature and speed.

5. The intelligent monitoring method for fumigant production according to claim 4, characterized in that: The multi-level constraint mechanism includes first-level constraint, second-level constraint and third-level constraint; Each constraint is introduced into the objective function through Lagrange multipliers, where , represents the Lagrange multiplier of the first-order constraint; Lagrange multipliers representing secondary constraints; Lagrange multipliers representing the three-level constraints; The objective function is to minimize energy consumption; The loss function is composed of the objective function and the penalty term of the constraint condition. The penalty term of each constraint condition is multiplied by the corresponding Lagrange multiplier, and the influence of the constraint on the optimization objective is controlled by weighting.

6. The intelligent monitoring method for fumigant liquid production according to claim 5, characterized in that: The simulated annealing algorithm is used to perform a global search for the preliminary optimized operating parameters, including: using the preliminary optimized operating parameters as an initial solution of the simulated annealing algorithm; setting an initial temperature value, and gradually reducing the temperature as the iteration proceeds; generating new candidate solutions by slightly perturbing the initial solution, and performing multiple rounds of iterations; Calculate the energy consumption difference between the current solution and the new solution. When the energy consumption of the new candidate solution is lower than that of the current solution, accept the new solution unconditionally. When the energy consumption of the new candidate solution is higher than that of the current solution, decide whether to accept the new solution based on the acceptance probability. When the temperature drops to the set low value or reaches the maximum number of iterations, the search stops and the optimal operating parameters of the fumigant liquid are output.

7. The intelligent monitoring method for fumigant liquid production according to claim 6, characterized in that: The iterating smart contract based on real-time data includes: the optimal operating parameters are fed back to the system through the blockchain as input for the next round of smart contract optimization.

8. An intelligent monitoring system for fumigant liquid production using the method according to any one of claims 1 to 7, characterized in that: The intelligent monitoring system includes: The data module collects energy consumption data during the fumigation liquid production process in real time through sensors and uploads it to the blockchain; The blockchain module verifies the legitimacy of the uploaded data. When the data is verified to be legitimate, it triggers the smart contract to execute optimization decisions and automatically adjust the operating parameters of the fumigant liquid; The iteration module adjusts the results through blockchain feedback and iterates the smart contract based on real-time data to ensure continuous improvement of the system.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the intelligent monitoring method for fumigant liquid production according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the intelligent monitoring method for fumigant liquid production according to any one of claims 1 to 7 are implemented.

Images