Intelligent laboratory environment automatic monitoring and adjusting method and system

Abstract

The invention discloses an intelligent laboratory environment automatic monitoring and adjusting method and system, and relates to the technical field of intelligent control, and the method comprises the steps: analyzing an experiment task, determining an environment demand vector, and configuring a standard environment adaptation curve; activating a multi-mode sensor to carry out environment perception, and constructing an environment state vector; the environment state vector is used as an initial state, and in a set search space, a standard environment adaptation curve is used as a constraint, and search optimization is executed through a three-dimensional balance optimization function; and formulating an environment regulation scheme based on an optimization result, and carrying out automatic regulation on the environment of the laboratory. The technical problems that existing laboratory environment control cannot respond to diversified environment requirements of different experiment tasks in time, and sufficient adaptability and flexibility are lacked in the face of environment sudden change are solved, automatic monitoring and quick response of the environment of a laboratory are achieved through intelligent environment perception and three-dimensional balance optimization, and the intelligent environment sensing and three-dimensional balance optimization are achieved. And the adaptability and flexibility of environment adjustment are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent control, and particularly to an intelligent automatic monitoring and adjusting method and system for a laboratory environment. Background Art

[0002] At present, the control of the laboratory environment mostly relies on manual adjustment and basic operations of single devices, lacking an intelligent and precise adjustment system. Traditional environmental monitoring methods often fail to respond promptly to the dynamic requirements of experimental tasks, resulting in large fluctuations in the experimental environment and affecting the accuracy and stability of experimental results. With the increasing complexity of scientific experiments, especially for experimental tasks with high environmental precision requirements (such as chemical reactions, biological experiments, etc.), traditional control methods can no longer meet the growing experimental needs.

[0003] Therefore, how to achieve automatic monitoring and adjustment of the laboratory environment through intelligent means to ensure that the laboratory environment is always in the optimal state has become a key technical challenge for improving the quality and efficiency of experiments. Summary of the Invention

[0004] This application provides an intelligent automatic monitoring and adjusting method and system for a laboratory environment to solve the technical problems that the existing laboratory environment control cannot respond promptly to the diverse environmental requirements of different experimental tasks and lacks sufficient adaptability and flexibility in the face of environmental mutations.

[0005] In the first aspect of this application, an intelligent automatic monitoring and adjusting method for a laboratory environment is provided. The method includes: parsing an experimental task, establishing environmental parameter requirements based on the experimental type and experimental stage, integrating the environmental parameter requirements into an environmental requirement vector, and configuring a standard environmental adaptation curve; activating multi-modal perception sensors to perform environmental perception of the laboratory and establishing an environmental state vector; creating a three-dimensional balance optimization function, where the balance evaluation features of the three-dimensional balance optimization function include cost features, environmental adaptation degree features, and mutation penalty features; using the environmental state vector as the initial state, after setting a search space, using the standard environmental adaptation curve as a constraint, and performing search and optimization through the three-dimensional balance optimization function; establishing an environmental adjustment plan based on the search and optimization results and performing automatic environmental adjustment of the laboratory based on the environmental adjustment plan.

[0006] In the second aspect of the present application, an intelligent laboratory environment automatic monitoring and adjustment system is provided. The system includes: an environmental requirement analysis module, which is used to analyze experimental tasks, establish environmental parameter requirements based on experimental types and experimental stages, integrate the environmental parameter requirements into an environmental requirement vector, and configure a standard environmental adaptation curve; an environmental state perception module, which is used to activate multi-modal perception sensors to perform environmental perception of the laboratory and establish an environmental state vector; an optimization function creation module, which is used to create a three-dimensional balance optimization function, and the balance evaluation features of the three-dimensional balance optimization function include cost features, environmental adaptation degree features, and mutation penalty features; an environmental adaptation optimization module, which is used to use the environmental state vector as the initial state, after setting the search space, use the standard environmental adaptation curve as a constraint, and perform search optimization through the three-dimensional balance optimization function; an environmental automatic adjustment module, which is used to establish an environmental adjustment plan based on the search optimization result and perform automatic environmental adjustment of the laboratory based on the environmental adjustment plan.

[0007] One or more technical solutions provided in the present application have at least the following technical effects or advantages: The intelligent laboratory environment automatic monitoring and adjustment method and system provided in the present application relate to the field of intelligent control technology. By analyzing experimental tasks, determining environmental parameter requirements, integrating them into an environmental requirement vector, configuring a standard environmental adaptation curve, activating multi-modal sensors for environmental perception, constructing an environmental state vector, and optimizing within a set search space with the standard environmental adaptation curve as a constraint, formulating an environmental adjustment plan, realizing the automatic adjustment of the laboratory environment, solving the technical problems that the existing laboratory environment control cannot respond in a timely manner to the diverse environmental requirements of different experimental tasks and lacks sufficient adaptability and flexibility in the face of environmental mutations, and achieving the technical effects of realizing automatic monitoring and rapid response of the environment in the laboratory through intelligent environmental perception and three-dimensional balance optimization, and improving the adaptability and flexibility of environmental adjustment. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0009] Figure 1 It is a schematic flow chart of the intelligent laboratory environment automatic monitoring and adjustment method provided in the embodiment of the present application; Figure 2Schematic diagram of the intelligent laboratory environment automatic monitoring and adjustment system provided by the embodiments of the present application.

[0010] Explanation of reference numerals: Environment requirement analysis module 11, environment status perception module 12, optimization function creation module 13, environment adaptation optimization module 14, environment automatic adjustment module 15. Specific implementation manners

[0011] The present application provides an intelligent laboratory environment automatic monitoring and adjustment method and system, which are used to solve the technical problems that the existing laboratory environment control cannot respond in time to the diverse environment requirements of different experimental tasks and lacks sufficient adaptability and flexibility in the face of environmental mutations.

[0012] Next, the technical solutions in the embodiments of the present application will be clearly and completely described with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the protection scope of the present application.

[0013] It should be noted that the terms "first", "second", etc. in the specification of the present application and the above-mentioned accompanying drawings are used to distinguish similar objects, and do not have to be used to describe a specific order or sequence. It should be understood that such used data can be interchanged under appropriate circumstances so that the embodiments of the present application described herein can be implemented in an order different from those illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or server including a series of steps or units does not have to be limited to those steps or units clearly listed, but may include other steps or modules not clearly listed or inherent to these processes, methods, products or devices.

[0014] Embodiment 1, as Figure 1 shown, the present application provides an intelligent laboratory environment automatic monitoring and adjustment method, and the method includes: P10: Analyze the experimental task, establish environmental parameter requirements based on the experimental type and experimental stage, integrate the environmental parameter requirements into an environmental requirement vector, and configure a standard environment adaptation curve.

[0015] Specifically, to achieve precise environmental control, it is first necessary to analyze the experimental tasks, that is, to conduct a detailed analysis of the experimental type and experimental stage to determine the environmental parameters required for the experiment. Experimental types include, but are not limited to, chemical experiments, physical experiments, biological experiments, etc. Each experimental type has different requirements for the experimental environment. For example, the requirements for environmental conditions such as temperature, humidity, and light intensity are different. In addition, different experimental stages will also affect the environmental requirements. In the initial stage of the experiment, relatively stable environmental conditions may be required, while in the later stage of the experiment, some environmental parameters may need to be adjusted according to the progress of the experiment. Therefore, it is necessary to establish different environmental parameter requirements based on the experimental type and experimental stage.

[0016] Among them, environmental parameter requirements refer to various environmental elements required under specific experimental conditions, such as temperature, humidity, air flow, light, etc. These parameters will have a direct impact on the experimental results. For example, in chemical experiments, temperature and humidity may need to be maintained within a very precise range, while in biological experiments, temperature, humidity, oxygen content, etc. may all affect the feasibility and accuracy of the experiment. These environmental parameter requirements will form an environmental requirement vector, which is a mathematical model that uniformly represents all environmental parameter requirements. The creation of the environmental requirement vector can help the system more clearly identify the specific environmental factors that need to be adjusted in different experimental tasks.

[0017] At the same time, in order to ensure that the experimental environment can meet these requirements, a standard environmental adaptation curve needs to be configured. The standard environmental adaptation curve is a preset and idealized curve of environmental parameter changes, which can be determined based on the existing equipment capabilities of the laboratory, experimental historical data, and the latest achievements of scientific research. It defines the ideal change trend of environmental parameters over time according to the characteristics of the experimental type and stage. For example, in biological culture experiments, the temperature may need to gradually increase or decrease within a certain period of time to simulate the diurnal temperature difference in the natural environment. The standard environmental adaptation curve provides a clear goal for the environmental regulation system, enabling the system to dynamically adjust the actual environmental parameters of the laboratory according to this curve to ensure that the experimental environment is always in the best state.

[0018] By analyzing the experimental tasks and establishing the environmental requirement vector and the standard environmental adaptation curve, this step provides a solid foundation for subsequent environmental perception, optimization, and regulation. This process not only improves the automation level of laboratory environmental control but also enhances the reliability and repeatability of experimental results.

[0019] P20: Activate the multi-modal perception sensors to perform environmental perception of the laboratory and establish an environmental state vector. Among them, the multi-modal perception sensors include temperature and humidity sensors, light sensors, air flow velocity and direction sensors, gas concentration sensors, dust particle sensors, and sample state imaging sensors.

[0020] Optionally, to achieve comprehensive perception and precise monitoring of the laboratory environment, this step activates multi-modal sensing sensors to perform comprehensive perception of the laboratory environment. These sensors will obtain various environmental data in the laboratory in real time through multiple different detection methods to ensure that the environment can be monitored and responded to in all aspects. Among them, multi-modal sensing refers to obtaining multi-dimensional information through different types of sensors, and these information complement each other to jointly form a complete perception system of the laboratory environment.

[0021] Specifically, the multi-modal sensing sensors used in this step include temperature and humidity sensors, light sensors, air flow velocity and direction sensors, gas concentration sensors, dust particle sensors, and sample state imaging sensors. These sensors work together to monitor the key environmental parameters in the laboratory in real time.

[0022] Among them, the temperature and humidity sensor is one of the most common environmental monitoring devices, which can measure the temperature and humidity levels in the air in real time. In the laboratory, especially for some chemical and biological experiments, changes in temperature and humidity may directly affect the stability and reliability of experimental results. Therefore, the application of temperature and humidity sensors is crucial.

[0023] The light sensor is used to measure the light intensity in the laboratory, especially in those experiments with strict requirements for light, such as the study of plant photosynthesis in biological experiments or the photosensitive reaction in chemical reactions. Changes in light intensity will directly affect the experimental results, so the light sensor provides necessary data support for the control of the laboratory environment.

[0024] The air flow velocity and direction sensor is used to measure the air flow velocity and direction. These data are crucial for air flow control in the laboratory, especially in cases where air quality or air flow direction affects the experiment, such as controlling the spread of pollution sources and ensuring the uniformity of gas exchange. Air flow plays a key role in the reaction and change of samples during the experiment.

[0025] The gas concentration sensor is used to monitor the concentration of gas components in the laboratory in real time, such as the concentration of oxygen, carbon dioxide, nitrogen, and harmful gases (such as ammonia, methane, etc.). In some experiments, changes in gas concentration will affect the accuracy and safety of the experiment. Therefore, timely grasping of gas concentration changes is crucial for ensuring the stability of the experimental environment.

[0026] The dust particle sensor is used to detect the concentration of tiny particles in the laboratory, especially those harmful particles that may affect the experimental results. During some experimental processes, dust and particles in the air may interfere with the experimental results and even affect the normal operation of equipment. Therefore, monitoring the presence and concentration changes of these particles is an important step to ensure the smooth progress of the experiment.

[0027] Finally, a sample status imaging sensor is used to obtain the status information of the sample during the experiment and provide real-time visual feedback. Through imaging technology, the change process of the sample can be dynamically observed, and its status changes can be analyzed through image data, providing intuitive image data for the analysis of experimental results.

[0028] All the data collected by these sensors will be aggregated and form an environmental status vector. The environmental status vector is a comprehensive data model formed by integrating the environmental data collected by different sensors, which can comprehensively reflect the current environmental status of the laboratory. Through this vector, the system can understand the real-time status of each environmental parameter in the laboratory and provide a basis for subsequent intelligent adjustment.

[0029] P30: Create a three-dimensional balance optimization function, and the balance evaluation features of the three-dimensional balance optimization function include cost features, environmental fitness features, and mutation penalty features.

[0030] Furthermore, step P30 of the embodiment of the present application further includes: P31: Obtain a task object based on the experimental task, perform sensitive perception of environmental mutations on the task object, and generate a first influence weight of the mutation penalty feature using the sensitive perception result; P32: Perform user physical sign interaction with the experimenter, perform comfortable influence perception of environmental mutations based on the user physical sign interaction result, and generate a second influence weight of the mutation penalty feature using the comfortable influence perception result; P33: Create a three-dimensional balance optimization function using the first influence weight and the second influence weight.

[0031] It should be understood that in order to achieve precise adjustment and optimization of the laboratory environment, a three-dimensional balance optimization function needs to be created. The balance evaluation features of this function include cost features, environmental fitness features, and mutation penalty features. The cost feature focuses on the economic cost required to adjust the experimental environment, the environmental fitness feature measures the matching degree between the experimental environment and the requirements of the experimental task, and the mutation penalty feature considers the possible negative impacts of sudden changes in the experimental environment on experimental results, equipment, and experimenters. In practical applications, the system will balance various factors in the process of environmental adjustment based on these feature weights to ensure the optimized adjustment of the experimental environment.

[0032] Specifically, in order to more precisely define the mutation penalty feature, first obtain a task object based on the experimental task and perform sensitive perception of environmental mutations on the task object. By analyzing the type and stage of the experimental task, determine the sensitivity of the experiment to environmental mutations. For example, biological culture experiments may be more sensitive to sudden changes in temperature and humidity, while physical experiments may be more sensitive to sudden changes in light and air flow rate. According to the sensitive perception result, generate a first influence weight of the mutation penalty feature, which reflects the sensitivity of the experimental task to environmental mutations.

[0033] Next, perform interactive perception on the physical signs of the experimental personnel. By monitoring the physiological state of the experimental personnel (such as heart rate, body temperature, etc.), evaluate the impact of environmental mutations on the comfort of the experimental personnel. When the laboratory environment mutates, the physical signs of the experimental personnel may change, resulting in discomfort or inconvenience. Therefore, it is necessary to perceive this impact on comfort. For example, a sudden change in temperature may cause discomfort to the experimental personnel, affecting work efficiency and safety. According to the perception results of comfort impact, generate the second impact weight of the mutation penalty feature, which reflects the potential impact of environmental mutations on the experimental personnel.

[0034] Finally, combine the above two weights, namely the first impact weight (the impact of equipment and samples) and the second impact weight (the impact on the comfort of the experimental personnel), to create the final three-dimensional balance optimization function. Exemplarily, as shown in the following formula: ; where is the cost feature, which represents the resource consumption or cost of environmental regulation, usually related to energy use, equipment operation, etc. The lower the cost, the more efficient the environmental regulation. is the environmental fitness feature, which measures the matching degree between the current laboratory environmental state and the requirements of the experimental task. The higher the fitness, the better the environmental regulation effect. is the mutation penalty feature, which represents the negative impact of environmental fluctuations or mutations on experimental results and experimental personnel. The greater the mutation impact, the higher the penalty, and the system will tend to avoid mutations. , is the weight coefficient, which represents the relative importance of each feature to the optimization goal. By adjusting these weights, the focus and trade-offs in the optimization process can be controlled. This function will consider all relevant factors and, through optimization calculations, obtain the most suitable environmental regulation plan to ensure the stability of the experimental environment, minimize resource consumption, while ensuring the comfort of experimental personnel and the accuracy of experimental results. To ensure that the experimental task can be carried out smoothly under the best conditions and minimize the interference of environmental mutations to the experiment.

[0035] Furthermore, step P33 of the embodiment of the present application further includes: P33-1: Perform external environmental data collection of the laboratory, perform natural fluctuation fitting of the laboratory using the external environmental data collection results and the standard environmental adaptation curve, and establish the third impact weight based on the fluctuation impact; P33-2: Configure the static weights of the three-dimensional balance optimization function based on the analysis results of the experimental task, and reconstruct the three-dimensional balance optimization function after performing reinforcement learning on the static weights using the first impact weight, the second impact weight, and the third impact weight.

[0036] Optionally, the construction process of the three-dimensional balance optimization function can be further refined to enhance the adaptability and accuracy of the environmental regulation scheme.

[0037] First, collect the external environment data of the laboratory, that is, through the sensor network deployed outside the laboratory, obtain the data of the external environment such as temperature, humidity, light intensity, wind speed, air quality, etc. in real time. The collected results of these external environment data will be compared and analyzed with the standard environment adaptation curve inside the laboratory to fit the natural fluctuations of the laboratory environment. For example, when the external temperature changes sharply, the temperature inside the laboratory will also be affected to a certain extent, and this natural fluctuation needs to be accurately identified and quantified. According to the degree of fluctuation impact, establish the third impact weight, which reflects the impact degree of external environment changes on the internal environment regulation requirements of the laboratory.

[0038] Next, based on the analysis results of the previous experimental tasks, configure the static weights of the three-dimensional balance optimization function. The analysis results of the experimental tasks provide the specific requirements of the experiment for environmental parameters, such as temperature range, humidity accuracy, etc., and these requirements are converted into static weights to initially define the importance of each feature in the three-dimensional balance optimization function. Then, use the first impact weight (the sensitivity of the experimental task to environmental mutations), the second impact weight (the potential impact of environmental mutations on experimental personnel), and the newly established third impact weight (the impact of external environment changes) to perform reinforcement learning on the static weights. Reinforcement learning is a machine learning method that optimizes the performance of the function by continuously trial and error and feedback to adjust the weights. In this process, the system will dynamically adjust each weight according to the actual environmental regulation effect and the completion situation of the experimental task, making the three-dimensional balance optimization function more in line with the actual needs of the laboratory.

[0039] Finally, through this reinforcement learning process based on the analysis results of experimental tasks and multi-dimensional impact weights, reconstruct the three-dimensional balance optimization function. The reconstructed function can more accurately reflect the complex requirements of laboratory environment regulation, while considering the sensitivity of internal experimental tasks, the comfort of personnel, and the volatility of the external environment. This enables the laboratory's environmental regulation system to respond more intelligently to various situations, ensuring that the experimental environment is always in the best state, improving the accuracy and reliability of experimental results, and also guaranteeing the health and safety of experimental personnel.

[0040] P40: Use the environmental state vector as the initial state. After setting the search space, use the standard environment adaptation curve as the constraint, and perform search optimization through the three-dimensional balance optimization function.

[0041] Furthermore, step P40 of the embodiment of the present application further includes: P41: Perform population initialization within the search space, where each individual in the population represents a candidate environmental regulation path; P42: Execute the satisfaction determination of the standard environmental adaptation curve for the individuals within the population and establish the satisfaction determination result; P43: Use the three-dimensional balance optimization function to evaluate the fitness of the individuals within the population and establish the fitness evaluation result; P44: Use the fitness evaluation result and the satisfaction determination result to iteratively update within the search space to perform search optimization.

[0042] Specifically, to achieve precise regulation and optimization of the laboratory environment, the environmental state vector can be used as the initial state, a search space can be set, and the three-dimensional balance optimization function can be used to perform search optimization with the standard environmental adaptation curve as the constraint condition. The environmental state vector represents the current environmental conditions of the laboratory, while the standard environmental adaptation curve provides a reference for the ideal environmental state. Through these two elements, the system can execute intelligent algorithms within the set search space to find the optimal environmental regulation path to achieve the best environmental adaptation.

[0043] First, perform population initialization within the search space. That is, randomly generate a certain number of initial solutions, and each solution represents a candidate environmental regulation path. Each individual in the population represents a possible environmental regulation scheme, and these schemes are randomly distributed in the search space at the initial stage to ensure the diversity of the population, thereby improving the global search ability of the algorithm.

[0044] Next, execute the satisfaction determination of the standard environmental adaptation curve for the individuals within the population and establish the satisfaction determination result. This process involves evaluating whether each individual meets the requirements of the standard environmental adaptation curve, that is, checking whether each candidate regulation path can make the laboratory environment reach or approach the ideal state. The satisfaction determination result will serve as an important basis for subsequent fitness evaluation.

[0045] Subsequently, use the three-dimensional balance optimization function to evaluate the fitness of the individuals within the population and establish the fitness evaluation result. Fitness evaluation is to calculate the fitness value of each individual according to the predefined three-dimensional balance optimization function. This value reflects the comprehensive performance of the individual in terms of cost, environmental fitness, and mutation penalty. The higher the fitness value, the closer the individual is to the optimal solution.

[0046] Finally, using the fitness evaluation results and satisfaction determination results, iterative updates are performed within the search space to execute search optimization. According to the fitness evaluation results, excellent individuals are selected, new candidate solutions are generated through operations such as crossover and mutation, and the search direction is adjusted according to the satisfaction determination results, gradually approaching the optimal solution. Through this iterative update mechanism, the algorithm can dynamically adjust within the search space and finally find the optimal environment regulation plan to achieve intelligent regulation of the laboratory environment. This process gradually narrows the search space and optimizes the environment regulation plan by continuously repeating fitness evaluation, satisfaction determination of the standard environment adaptation curve, and update until the optimal solution is found.

[0047] Through these steps, the system can intelligently adjust the laboratory environment, ensure the smooth progress of experimental tasks under optimal environmental conditions, and at the same time reduce the impact of resource consumption and environmental mutations on experimental results.

[0048] Furthermore, step P44 of the embodiment of the present application further includes: P44-1: In each iteration, determine the perturbation risk of the candidate environmental regulation path of each individual in the population as follows: ; where represents the perturbation risk assessment value of individual at iteration number , is the environmental fluctuation sensitivity weight coefficient, is the laboratory environmental state vector at the current iteration number , is the task object risk sensitivity weight coefficient, represents the impact evaluation function of the current regulation path on the task object, is the discomfort impact sensitivity weight coefficient, represents the negative quantification result of the impact of the current regulation path on comfort; P44-2: If the perturbation risk assessment value meets the preset threshold, the perturbation risk determination passes and the rollback mechanism is triggered; P44-3: Use the rollback mechanism for iterative update management.

[0049] In a possible embodiment of the present application, in addition to the previously described population initialization, fitness evaluation, and search optimization, it further includes a process of determining the perturbation risk of the candidate environmental regulation path of each individual in the population.

[0050] First, it is necessary to determine the perturbation risk of the candidate environmental regulation path of each individual in the population. The core of this process is to calculate the perturbation risk assessment value through the above formula. Exemplarily, first evaluate the fluctuation of the laboratory environment, which is represented by the magnitude of the environmental fluctuation, that is, the difference between the current environmental state and the target environmental state. This difference is represented by Quantify to reflect the amplitude of environmental changes. Fluctuations in the environment may have a direct impact on the experiment, and greater fluctuations may bring higher perturbation risks. Therefore, the magnitude of the fluctuations will directly affect the perturbation risk assessment value.

[0051] Next, the system will consider the biological risk assessment of the task object, that is , and this assessment value reflects the risks that environmental changes may pose to the experimental objects (such as equipment, samples, or personnel). Different task objects have different sensitivities when facing environmental fluctuations. Therefore, the system calculates the biological risk for each task object according to its characteristics to further correct the perturbation risk assessment value.

[0052] Then, the system will also consider the impact of the environment on the comfort of the experimental personnel, specifically manifested as , which indicates the discomfort that the current environmental adjustment path may cause to the experimental personnel. Experimental personnel working in an uncomfortable environment may affect their efficiency and even pose health risks. Therefore, changes in comfort also need to be incorporated into the perturbation risk assessment. The system quantifies this impact through the comfort assessment value to adjust the weight of the perturbation risk.

[0053] The combined effect of all these factors enables the system to calculate the perturbation risk assessment value for each individual. Combine environmental fluctuations, the biological risk of the task object, and the impact of comfort through specific calculation formulas to calculate the perturbation risk assessment value for each environmental adjustment path.

[0054] Next, compare the calculated perturbation risk assessment value with a preset threshold. If the assessment value exceeds the set threshold, it means that the current adjustment path may pose excessive risks to the experimental results or the experimental personnel. At this time, the system will trigger a rollback mechanism. The role of the rollback mechanism is to revoke the current environmental adjustment path and restore to a safer and more appropriate environmental state. This process can prevent excessive environmental fluctuations or discomfort to the experimental personnel, thus ensuring the smooth progress of the experiment.

[0055] Furthermore, the rollback mechanism will be used for iterative update management. Rollback is not just about withdrawing a certain adjustment path, but also managing and optimizing the adjustment process in new iterations. The system will continuously monitor and provide feedback to gradually adjust the laboratory environment and optimize the adjustment path to ensure that the experiment can gradually approach the optimal solution in each round of iteration. The rollback mechanism ensures that when facing excessive perturbation risks, the system can adjust in a timely manner to avoid other problems caused by experimental failures or environmental discomfort, thus maintaining the stability and safety of the environment throughout the experimental process.

[0056] Through this coherent execution process, it is possible to effectively manage the adjustment of the laboratory environment, reduce the impact of external environmental fluctuations, ensure the smooth progress of the experiment, and maintain the comfort of the experimental personnel and the accuracy of the experimental results throughout the experiment.

[0057] Furthermore, step P44-3 of the embodiment of the present application further includes: P44-31: After the rollback mechanism is triggered, perform perturbation comparison of the path points within the window based on the historical iteration window to locate the path point with the minimum perturbation; P44-32: Perform iterative rollback based on the path point with the minimum perturbation and establish a reverse perturbation based on the original search direction; P44-33: Perform iterative update management according to the iterative rollback and the reverse perturbation.

[0058] It should be understood that the specific implementation of the rollback mechanism can be further refined. When the rollback mechanism is triggered, perturbation comparison of the path points is performed based on the historical iteration window. The historical iteration window contains the environmental adjustment path data recorded in multiple previous iteration steps. The system will compare these path points and evaluate the performance of each path point during the perturbation process. The goal is to find the path point with the minimum perturbation through comparison, that is, among the historical path points, the path point with the least impact of environmental fluctuations on the experimental results and the experimental personnel. This path point with the minimum perturbation represents a relatively stable and most adaptable environmental adjustment state and is the optimal starting point reselected after rollback.

[0059] Then, based on the found path point with the minimum perturbation, perform iterative rollback. At this time, the system not only restores to a certain historical path point but also needs to establish a reverse perturbation based on the original search direction, that is, through an adjustment method opposite to the current path point, the experimental environment is corrected in the reverse direction. The purpose of the reverse perturbation is to eliminate the excessive perturbation caused by the current path to the experiment through reverse adjustment, and then re-guide the environment to transition to a more stable state that meets the experimental requirements, ensuring that the rollback is not just a simple cancellation of the adjustment but a systematic reverse correction to gradually return to a suitable adjustment state.

[0060] Subsequently, perform iterative update management according to the iterative rollback and the reverse perturbation. In this stage, the rollback mechanism and the reverse perturbation will be incorporated into the subsequent environmental adjustment process to form a new iteration cycle. In this cycle, the system will continue to optimize the environmental adjustment path and perform real-time monitoring to ensure that the path after rollback can effectively reduce the perturbation risk and generate the optimal environmental adjustment plan. Through this iterative update management, the system can continuously adjust the laboratory environment, gradually approach the optimal solution, and ensure that the experimental task can be carried out more stably in each round of iteration to improve the adaptability of the system to environmental changes.

[0061] Furthermore, step P40 of the embodiment of the present application further includes: P41a: After each round of search is completed, the concentration degree of the current round of iterative solution is judged by the Kullback-Leibler (K-L) divergence; P42a: If the concentration degree meets the concentration threshold mapped with the number of iterations, the subspace jump mechanism is triggered; P43a: The subspace jump mechanism is used to update the current round of iterative solution to complete the search optimization.

[0062] Optionally, after each round of search is completed, the Kullback-Leibler (K-L) divergence can be used to judge the concentration degree of the current round of iterative solution. The K-L divergence is a method to measure the difference between two probability distributions. In this application, the system uses the K-L divergence to evaluate the concentration degree of each candidate environmental regulation path in the current population. A concentrated solution usually means that most of the path points are concentrated in one area, indicating that the current search process may fall into a local optimal solution. If the solution is dispersed, it indicates that the explored space is wider and a more comprehensive solution may be obtained. By calculating the K-L divergence of the current solution, the system can judge whether it is necessary to further adjust the search strategy, especially when the search results are concentrated.

[0063] Next, the concentration degree is compared with the concentration threshold mapped with the preset number of iterations. If the current concentration degree meets this threshold, it indicates that the current search progress may be too concentrated and the search space may not be fully explored. At this time, the system will trigger the subspace jump mechanism. The purpose of the subspace jump mechanism is to help the system jump out of the current local optimal solution area and explore a wider solution space by making a large jump in the search space. By triggering this mechanism, the system can avoid falling into the local optimal solution and enhance the global search ability.

[0064] Finally, the subspace jump mechanism is used to update the current round of iterative solution. The search space is re-divided or the search direction is adjusted to expand the search scope and avoid continuing to linger in the original solution set area. When performing the subspace jump, the algorithm will dynamically adjust the search strategy according to the concentration degree of the current solution and the preset threshold, which may include changing the search direction, increasing the search step size or making a random jump in the search space, etc. In this way, the algorithm can enhance the global search ability while maintaining the fineness of local search, thereby increasing the probability of finding the optimal solution.

[0065] In addition, during the process of using the subspace jump mechanism to update the current round of iterative solution, the path points in the search space can be perturbed and compared to locate the minimum perturbation path point, and iterative rollback is performed based on the minimum perturbation path point, and a reverse perturbation is established based on the original search direction. These steps help to more precisely control the update and adjustment of the solution when performing search optimization, ensuring that the algorithm can effectively balance the needs of local search and global search.

[0066] P50: Establish an environmental regulation plan based on the search and optimization results, and perform automatic environmental regulation in the laboratory based on the environmental regulation plan.

[0067] Specifically, based on the results of the aforementioned search and optimization, an environmental regulation plan is finally established, and the automatic regulation of the laboratory environment is carried out based on the environmental regulation plan. This environmental regulation plan usually includes the specific regulation values of multiple environmental parameters such as temperature, humidity, air velocity, and gas concentration, as well as how to dynamically adjust these parameters at different experimental stages or conditions. Each regulation plan is based on the previous search results to ensure that it meets the requirements of the experimental task, while also optimizing the use of laboratory resources and reducing unnecessary energy consumption.

[0068] Specifically, first, determine the optimal environmental regulation plan based on the search and optimization results, which includes the ideal setting values of key environmental parameters such as temperature, humidity, and light. These setting values are obtained based on the previous iterative optimization process, which takes into account the cost characteristics, environmental adaptability characteristics, and mutation penalty characteristics to ensure that the regulation plan not only meets the experimental requirements but also takes into account energy efficiency and adaptability to environmental mutations.

[0069] Next, apply these optimal setting values to the automatic regulation equipment in the laboratory, such as temperature controllers, humidity regulators, and light regulation systems. These devices will automatically adjust the laboratory environment according to the preset regulation plan to match the specific requirements of the experiment. This automatic regulation process not only improves the efficiency and accuracy of regulation but also reduces the need for human intervention, thereby reducing the possibility of operation errors.

[0070] In addition, according to the search results, the core goal of the intelligent greenhouse environmental control system is to achieve optimal management of key factors such as temperature, humidity, and carbon dioxide concentration through precise environmental monitoring and regulation, thereby providing the most suitable environmental conditions for plant growth. Through this solution, combined with modern sensing technology, automatic control equipment, 4G communication technology, and intelligent decision support systems, the greenhouse management efficiency can be effectively improved, manual intervention can be reduced, resource use can be optimized, and the intelligence, precision, and efficiency of agricultural production can be achieved. This solution is also applicable to the automatic regulation of the laboratory environment. By integrating various sensors such as temperature and humidity sensors, carbon dioxide concentration sensors, and wind speed sensors, the environmental parameters in the laboratory are monitored in real time. The system uploads this data to the cloud platform through the 4G communication module. After data analysis, the environmental conditions in the laboratory, such as temperature, humidity, carbon dioxide concentration, and light intensity, are automatically adjusted to ensure that plants thrive in the best growth environment. At the same time, the system supports users to perform remote monitoring and management through mobile devices or the Web end.

[0071] In this way, the laboratory environment adjustment scheme can achieve a high degree of automation and intelligence, ensuring the consistency and repeatability of experimental conditions, thereby improving the reliability and practicality of experimental results. At the same time, laboratory managers can use the system to uniformly manage information such as the experimental progress and experimental personnel, improving the overall operation efficiency of the laboratory.

[0072] Furthermore, the embodiment of the present application further includes step P60, and step P60 further includes: P61: Activate the multi-modal perception sensor to collect the environmental changes in the laboratory and establish a time-series change data set; P62: Perform the achievement verification of the environmental adjustment scheme according to the time-series change data set; P63: Generate a secondary compensation adjustment scheme according to the achievement verification result.

[0073] In a possible embodiment of the present application, the environmental adjustment scheme can be continuously optimized.

[0074] First, activate the multi-modal perception sensor to collect the environmental changes in the laboratory and establish a time-series change data set. In this link, the multi-modal perception sensor network is used to continuously monitor the changes in key environmental parameters such as temperature, humidity, light intensity, and gas concentration in the laboratory. By continuously collecting these data, the system can establish a detailed time-series change data set, which records the changes in environmental parameters over time. These data are crucial for verifying the implementation effect of the environmental adjustment scheme because they provide direct evidence of the actual environmental state.

[0075] Next, perform the achievement verification of the environmental adjustment scheme according to the time-series change data set. Using the established time-series change data set, the system will verify whether the adjustment scheme has achieved the expected effect by comparing with the target values set in the environmental adjustment scheme. This includes checking whether the environmental parameters have reached the set values within the specified time and whether these parameters can be stabilized within the ideal range. The achievement verification is a key step, which ensures that the environmental adjustment scheme is not only theoretically effective but also can produce the expected results in practice.

[0076] Furthermore, generate a secondary compensation adjustment scheme according to the achievement verification result. If it is found during the achievement verification process that the environmental adjustment scheme fails to fully achieve the expected goals or the stability of the environmental parameters is not ideal enough, a secondary compensation adjustment scheme can be generated based on this information, including fine-tuning the initial adjustment parameters, introducing additional adjustment measures, or improving the adjustment strategy, etc. The purpose of this link is to further improve the accuracy and reliability of environmental adjustment through continuous feedback and adjustment, ensuring that the laboratory environment is always in the best state.

[0077] Through these steps, a closed-loop control system is implemented to automatically monitor, verify, and adjust the laboratory environment, ensuring that each experimental stage can be carried out in a compliant environment, thereby improving the reliability and accuracy of experimental results.

[0078] In summary, the embodiments of the present application at least have the following technical effects: The present application analyzes the experimental tasks, determines the environmental parameter requirements based on the experimental type and stage, integrates them into an environmental requirement vector, and configures a standard environmental adaptation curve; activates multi-modal sensors for environmental perception to construct an environmental state vector; within the set search space, uses the three-dimensional balance optimization function for optimization with the adaptation curve as a constraint; finally, formulates an environmental adjustment plan based on the optimization results to achieve automatic adjustment of the laboratory environment.

[0079] It achieves the technical effects of realizing automatic monitoring and rapid response of the laboratory environment through intelligent environmental perception and three-dimensional balance optimization, and improving the adaptability and flexibility of environmental adjustment.

[0080] Embodiment 2, based on the same inventive concept as the intelligent laboratory environment automatic monitoring and adjustment method in the foregoing embodiment, as Figure 2 shown, the present application provides an intelligent laboratory environment automatic monitoring and adjustment system. The system in the embodiments of the present application and the method embodiments are based on the same inventive concept. Among them, the system includes: An environmental requirement analysis module 11, which is used to analyze the experimental tasks, establish environmental parameter requirements based on the experimental type and experimental stage, integrate the environmental parameter requirements into an environmental requirement vector, and configure a standard environmental adaptation curve.

[0081] An environmental state perception module 12, which is used to activate multi-modal perception sensors to perform environmental perception of the laboratory and establish an environmental state vector.

[0082] An optimization function creation module 13, which is used to create a three-dimensional balance optimization function. The balance evaluation features of the three-dimensional balance optimization function include cost features, environmental adaptability features, and mutation penalty features.

[0083] An environmental adaptation optimization module 14, which is used to use the environmental state vector as the initial state. After setting the search space, with the standard environmental adaptation curve as a constraint, perform search optimization through the three-dimensional balance optimization function.

[0084] An environmental automatic adjustment module 15, which is used to establish an environmental adjustment plan based on the search optimization results and perform automatic adjustment of the laboratory environment based on the environmental adjustment plan.

[0085] Furthermore, the environmental state perception module 12 is further configured to perform the following steps: The multi-modal perception sensors include a temperature and humidity sensor, a light sensor, an air flow velocity and direction sensor, a gas concentration sensor, a dust particle sensor, and a sample state imaging sensor.

[0086] Furthermore, the optimization function creation module 13 is further configured to perform the following steps: Based on the experimental task, obtain a task object, perform sensitive perception of environmental mutations on the task object, and generate a first influence weight of mutation penalty features using the sensitive perception result; perform user physical sign interaction of the experimenter, perform comfort impact perception of environmental mutations based on the user physical sign interaction result, and generate a second influence weight of mutation penalty features using the comfort impact perception result; create a three-dimensional balance optimization function using the first influence weight and the second influence weight.

[0087] Furthermore, the optimization function creation module 13 is further configured to perform the following steps: Perform external environmental data collection of the laboratory, perform natural fluctuation fitting of the laboratory using the external environmental data collection result and the standard environmental adaptation curve, establish a third influence weight according to the fluctuation impact; configure the static weight of the three-dimensional balance optimization function based on the analysis result of the experimental task, and reconstruct the three-dimensional balance optimization function after performing reinforcement learning on the static weight using the first influence weight, the second influence weight, and the third influence weight.

[0088] Furthermore, the environmental adaptation optimization module 14 is further configured to perform the following steps: Perform population initialization within the search space, and each individual in the population represents a candidate environmental regulation path; perform satisfaction determination of the standard environmental adaptation curve for the individuals within the population, and establish a satisfaction determination result; perform fitness evaluation of the individuals within the population using the three-dimensional balance optimization function, and establish a fitness evaluation result; update and iteratively update within the search space using the fitness evaluation result and the satisfaction determination result to perform search optimization.

[0089] Furthermore, the environmental adaptation optimization module 14 is further configured to perform the following steps: In each iteration, perform perturbation risk determination on the candidate environmental regulation path of each individual within the population as follows: ; where represents the individual in the iteration number of the perturbation risk assessment value, is the environmental fluctuation sensitivity weight coefficient, the current iteration number The laboratory environment state vector below, is the risk sensitivity weight coefficient of the task object, representing the impact evaluation function of the current adjustment path on the task object, is the discomfort impact sensitivity weight coefficient, representing the negative quantization result of the impact of the current adjustment path on comfort; if the perturbation risk assessment value meets the preset threshold, the perturbation risk determination passes, triggering the rollback mechanism; using the rollback mechanism for iterative update management.

[0090] Furthermore, the environment adaptation optimization module 14 is also used to perform the following steps: After the rollback mechanism is triggered, based on the historical iteration window, perform path point perturbation comparison within the window to locate the minimum perturbation path point; perform iterative rollback based on the minimum perturbation path point, and establish reverse perturbation based on the original search direction; perform iterative update management according to the iterative rollback and the reverse perturbation.

[0091] Furthermore, the environment adaptation optimization module 14 is also used to perform the following steps: After each round of search is completed, judge the concentration of the iterative solution of the current round through the K-L divergence; if the concentration meets the concentration threshold mapped to the number of iterations, trigger the subspace jump mechanism; use the subspace jump mechanism to update the iterative solution of the current round to complete the search optimization.

[0092] Furthermore, the system also includes a verification compensation module, which is used to perform the following steps: Activate the multi-modal perception sensor to collect the environmental changes in the laboratory, establish a time-series change data set; perform the achievement verification of the environmental adjustment plan according to the time-series change data set; generate a secondary compensation adjustment plan according to the achievement verification result.

[0093] It should be noted that the above sequence of the embodiments of the present application is only for description and does not represent the superiority or inferiority of the embodiments. And the above describes specific embodiments of this specification. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are also possible or may be advantageous.

[0094] The above are only the preferred embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

[0095] This specification and the drawings are merely illustrative of the present application and are considered to cover any and all modifications, variations, combinations, or equivalents within the scope of the present application. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalent technologies, the present application is intended to include these changes and modifications.

Claims

1. An intelligent automatic monitoring and adjustment method for laboratory environment, characterized in that, The method includes: Analyze the experimental task, establish environmental parameter requirements based on the experimental type and experimental stage, integrate the environmental parameter requirements into an environmental requirement vector, and configure a standard environmental adaptation curve; Activate the multi-modal perception sensor to perform environmental perception in the laboratory and establish an environmental state vector; Create a three-dimensional balance optimization function, and the balance evaluation features of the three-dimensional balance optimization function include cost features, environmental adaptability features, and mutation penalty features; Take the environmental state vector as the initial state. After setting the search space, use the standard environmental adaptation curve as a constraint, and perform search optimization through the three-dimensional balance optimization function; Establish an environmental adjustment plan based on the search optimization result, and perform automatic environmental adjustment in the laboratory based on the environmental adjustment plan.

2. The intelligent laboratory environment automatic monitoring and adjusting method according to claim 1, wherein The creation of the three-dimensional balance optimization function includes: Obtain a task object based on the experimental task, perform sensitive perception of environmental mutations on the task object, and generate a first influence weight of the mutation penalty feature using the sensitive perception result; Perform user physical sign interaction of the experimenter, perform comfortable influence perception of environmental mutations based on the user physical sign interaction result, and generate a second influence weight of the mutation penalty feature using the comfortable influence perception result; Create a three-dimensional balance optimization function using the first influence weight and the second influence weight.

3. The intelligent laboratory environment automatic monitoring and adjustment method according to claim 2, characterized in that, The creation of the three-dimensional balance optimization function using the first influence weight and the second influence weight includes: Perform external environmental data collection in the laboratory, perform natural fluctuation fitting of the laboratory using the external environmental data collection result and the standard environmental adaptation curve, and establish a third influence weight based on the fluctuation influence; Configure the static weight of the three-dimensional balance optimization function based on the analysis result of the experimental task. After performing reinforcement learning on the static weight using the first influence weight, the second influence weight, and the third influence weight, reconstruct the three-dimensional balance optimization function.

4. The intelligent laboratory environment automatic monitoring and adjustment method according to claim 1, characterized in that, The performing search optimization through the three-dimensional balance optimization function with the standard environmental adaptation curve as a constraint after setting the search space includes: Perform population initialization within the search space, and each individual in the population represents a candidate environmental adjustment path; Perform satisfaction determination of the standard environmental adaptation curve for the individuals within the population and establish a satisfaction determination result; Perform fitness evaluation of the individuals within the population using the three-dimensional balance optimization function and establish a fitness evaluation result; Use the fitness evaluation result and the satisfaction determination result to perform iterative update within the search space to perform search optimization.

5. The intelligent laboratory environment automatic monitoring and adjustment method according to claim 4, characterized in that, The performing search optimization by using the fitness evaluation result and the satisfaction determination result to perform iterative update within the search space includes: In each iteration, perform perturbation risk determination on the candidate environmental adjustment path of each individual within the population as follows: ； Among them, characterize the individual at the number of iterations of the perturbation risk assessment value, is the environmental fluctuation sensitivity weight coefficient, the current number of iterations of the laboratory environmental state vector, is the task object risk sensitivity weight coefficient, characterize the evaluation function of the influence of the current adjustment path on the task object, is the discomfort influence sensitivity weight coefficient, characterize the negative quantification result of the influence of the current adjustment path on comfort; If the perturbation risk assessment value meets the preset threshold, the perturbation risk determination passes, and the rollback mechanism is triggered; Use the rollback mechanism to perform iterative update management.

6. The intelligent laboratory environment automatic monitoring and adjusting method according to claim 5, wherein The triggering of the rollback mechanism includes: After the rollback mechanism is triggered, perform perturbation comparison of the path points within the window based on the historical iteration window to locate the minimum perturbation path point; Perform iterative rollback based on the minimum perturbation path point and establish a reverse perturbation based on the original search direction. Perform iterative update management according to the iterative rollback and the reverse perturbation.

7. The intelligent laboratory environment automatic monitoring and adjustment method according to claim 1, characterized in that, The search optimization performed by the three-dimensional balance optimization function further includes: After each round of search is completed, judge the concentration of the iterative solution in the current round through the K-L divergence; If the concentration meets the concentration threshold mapped to the number of iterations, trigger the subspace jump mechanism; Use the subspace jump mechanism to update the iterative solution in the current round to complete the search optimization.

8. The intelligent laboratory environment automatic monitoring and adjusting method according to claim 1, characterized in that, After the environmental automatic adjustment of the laboratory is performed based on the environmental adjustment plan, it includes: Activate the multi-modal perception sensor to perform the acquisition of environmental changes in the laboratory and establish a time-series change data set; Perform the achievement verification of the environmental adjustment plan according to the time-series change data set; Generate a secondary compensation adjustment plan according to the achievement verification result.

9. The intelligent laboratory environment automatic monitoring and adjustment method according to claim 1, characterized in that, The multi-modal perception sensor includes a temperature and humidity sensor, a light sensor, an air flow velocity and direction sensor, a gas concentration sensor, a dust particle sensor, and a sample state imaging sensor.

10. An intelligent laboratory environment automatic monitoring and adjustment system, characterized in that, The system includes: An environmental requirement analysis module, which is used to analyze the experimental task, establish environmental parameter requirements based on the experimental type and experimental stage, integrate the environmental parameter requirements into an environmental requirement vector, and configure a standard environmental adaptation curve; An environmental state perception module, which is used to activate the multi-modal perception sensor to perform environmental perception in the laboratory and establish an environmental state vector; An optimization function creation module, which is used to create a three-dimensional balance optimization function, and the balance evaluation features of the three-dimensional balance optimization function include cost features, environmental adaptability features, and mutation penalty features; An environmental adaptation optimization module, which is used to use the environmental state vector as the initial state, after setting the search space, use the standard environmental adaptation curve as a constraint, and perform search optimization through the three-dimensional balance optimization function; An environmental automatic adjustment module, which is used to establish an environmental adjustment plan based on the search optimization result and perform environmental automatic adjustment of the laboratory based on the environmental adjustment plan.

Images