Laboratory environment intelligent adjusting system, monitoring method thereof and electronic equipment

Abstract

The embodiment of the invention discloses a laboratory environment intelligent adjusting system and a monitoring method thereof, and electronic equipment, and the system comprises the following parts: a data collection unit which is used for obtaining first environment time sequence data of a laboratory in real time, and carrying out the preprocessing of the first environment time sequence data, and obtaining second environment time sequence data; the analysis unit is used for inputting the second environment time sequence data into a trained quantum kernel discriminant analysis model and outputting a classification category of the second environment time sequence data; the recording unit is used for recording the second environment time series data as abnormal data when the classification category of the second environment time series data is inappropriate; and the adjusting unit is used for executing automatic adjustment according to the abnormal data. Abnormality of laboratory environment data can be monitored in real time, it can be guaranteed that the temperature and humidity of the laboratory environment are within a proper range, it is avoided that various measured values are affected by experiment conditions in an experiment, and intelligence of the laboratory is improved.

Description

Technical Field

[0001] The embodiments of the present invention relate to the technical field of laboratory environment monitoring, and in particular to an intelligent laboratory environment adjustment system and a monitoring method and electronic equipment thereof. Background Art

[0002] As an important link in data output, the laboratory must do a good job in data output quality control to ensure the accuracy of monitoring data. However, in the laboratory analysis process, there are many influencing factors, which lead to improper control of details and random or systematic errors. For example, changes in the laboratory environment affect the accuracy of the measurement results.

[0003] The laboratory environment mainly refers to the temperature and humidity of the laboratory, which will directly affect the quality of monitoring data. For example, if the temperature is too low, the color development reaction of total phosphorus will be incomplete, and if the temperature is too high, the column temperature of the ion chromatograph cannot be reduced, making the instrument unable to operate normally. Therefore, laboratory environment monitoring and adjustment are crucial. Summary of the invention

[0004] In order to overcome the shortcomings of the prior art, the purpose of the embodiments of the present invention is to provide a laboratory environment intelligent adjustment system and its monitoring method and electronic equipment, which can monitor laboratory environmental data in real time and intelligently adjust the laboratory environmental data when the monitored environmental time series data is classified as unsuitable, which is conducive to ensuring the temperature and humidity suitability of the laboratory.

[0005] To solve the above problems, the first aspect of the embodiment of the present invention discloses a laboratory environment intelligent adjustment system, which includes the following steps:

[0006] The data acquisition unit is used to obtain the first environmental time series data of the laboratory in real time, and pre-process the first environmental time series data to obtain the second environmental time series data, wherein the second environmental time series data I=(I 1 ,I 2 ,...Ia,...In), where, I 1 is the environmental time series data of the first monitoring point, Ia is the environmental time series data of the a-th monitoring point, In is the environmental time series data of the n-th monitoring point, and a and n are both natural numbers;

[0007] An analysis unit, used for inputting the second environment time series data into a trained quantum nuclear discriminant analysis model, and outputting classification categories of the second environment time series data, wherein the classification categories include three categories: suitable, relatively suitable, and unsuitable;

[0008] A recording unit, configured to record the second environment time series data as abnormal data when the classification category of the second environment time series data is inappropriate;

[0009] An adjustment unit is used to perform automatic adjustment according to the abnormal data.

[0010] Furthermore, the adjustment unit includes:

[0011] A determination unit, configured to determine an abnormal risk level according to the abnormal data, and perform automatic adjustment according to the abnormal risk level, wherein the abnormal risk level includes three levels: mild abnormality, moderate abnormality, and severe abnormality;

[0012] The control unit is used to adjust the air conditioning equipment and dehumidifier when mild and moderate abnormalities occur, and to shut down the experimental equipment that meets the preset conditions according to the experimental equipment operation data when serious abnormalities occur.

[0013] A second aspect of an embodiment of the present invention discloses a monitoring method for a laboratory environment intelligent adjustment system, which comprises the following steps:

[0014] Acquire the first environment time series data of the laboratory in real time, and preprocess the first environment time series data to obtain the second environment time series data, wherein the second environment time series data I=(I 1 ,I 2 ,...Ia,...In), where, I 1 is the environmental time series data of the first monitoring point, Ia is the environmental time series data of the a-th monitoring point, In is the environmental time series data of the n-th monitoring point, and a and n are both natural numbers;

[0015] Inputting the second environmental time series data into the trained quantum kernel discriminant analysis model, and outputting the classification categories of the second environmental time series data, wherein the classification categories include three categories: suitable, relatively suitable, and unsuitable;

[0016] When the classification category of the second environment time series data is inappropriate, the second environment time series data is recorded as abnormal data;

[0017] Automatic adjustment is performed based on the abnormal data.

[0018] Furthermore, the second environment time series data is input into the trained quantum kernel discriminant analysis model, and the classification category of the second environment time series data is output, including:

[0019] The quantum kernel discriminant analysis model encodes the second environment time series data to obtain new quantum state data, and then calculates the kernel matrix through the kernel function of the quantum kernel discriminant analysis model, obtains the similarity data of the quantum state through the kernel matrix, performs feature mapping on the similarity data, and then determines the projection position according to the mapping data after feature mapping and the projection direction, and outputs the category corresponding to the training data closest to the projection position in the projection space as the category of the second environment time series data; the projection direction is determined by solving the generalized eigenvalues ​​based on the intra-class divergence matrix Sw and the inter-class divergence matrix Sb of each category.

[0020] Furthermore, the kernel function of the quantum kernel discriminant analysis model is Among them, x i is the environmental time series data of the ith monitoring point, x i is the environmental time series data of the jth monitoring point, K(x i ,x j ) is the similarity between the quantum state of the environmental time series data of the ith monitoring point and the quantum state of the environmental time series data of the jth monitoring point, γ is a constant, is the quantum state of the environmental time series data of the i-th monitoring point, is the quantum state of the environmental time series data of the jth monitoring point.

[0021] Furthermore, the quantum kernel discriminant analysis model is trained by the following method:

[0022] The third environment time series data of each monitoring point running different numbers of experimental equipment at each time point is obtained as a training set, and training is performed using the third environment time series data. The time points divide a month into m time points at equal time intervals, where m is a natural number. The environment time series data includes temperature and humidity data, experimental equipment operation data, and time information data.

[0023] Further, performing automatic adjustment according to the abnormal data includes:

[0024] Determine the abnormal risk level according to the abnormal data, and perform automatic adjustment according to the abnormal risk level, wherein the abnormal risk level includes three levels: mild abnormality, moderate abnormality and severe abnormality; or, perform automatic adjustment after determining the target adjustment strategy through an optimization algorithm.

[0025] 9. Further, determining the abnormal risk level according to the abnormal data includes:

[0026] Obtain the comfortable temperature and humidity data of the laboratory, and determine that the abnormal data deviates from the comfortable temperature and humidity data by more than or equal to the first deviation data as a mild abnormality, the abnormal data deviates from the comfortable temperature and humidity data by more than or equal to the second deviation data as a moderate abnormality, and the abnormal data deviates from the comfortable temperature and humidity data by more than or equal to the third deviation data as a severe abnormality.

[0027] The third aspect of an embodiment of the present invention discloses an electronic device, characterized in that it includes: a memory storing executable program code; a processor coupled to the memory; the processor calls the executable program code stored in the memory to execute the monitoring method of the laboratory environment intelligent adjustment system disclosed in the second aspect of the embodiment of the present invention.

[0028] A fourth aspect of an embodiment of the present invention discloses a computer-readable storage medium, characterized in that it stores a computer program, wherein the computer program enables a computer to execute the monitoring method of a laboratory environment intelligent adjustment system disclosed in the second aspect of an embodiment of the present invention.

[0029] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0030] The present invention inputs the preprocessed second environment time series data into a trained quantum kernel discriminant analysis model, utilizes the similarity reflected by the quantum kernel function value, and projects the second environment time series data into the discriminant space for classification, thereby monitoring the anomalies of the laboratory environment data in real time, and then automatically adjusting the abnormal data, thereby facilitating ensuring that the temperature and humidity of the laboratory environment are within an appropriate range, avoiding various measurement values ​​in the experiment, such as concentration, reaction rate, pH in chemical experiments, and biological sample characteristics in biological experiments, being affected by the experimental conditions, and improving the intelligence of the laboratory. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 It is a flow chart of a monitoring method of a laboratory environment intelligent adjustment system provided by one embodiment of the present invention;

[0032] Figure 2 It is a structural schematic diagram of a laboratory environment intelligent adjustment system provided by one embodiment of the present invention;

[0033] Figure 3 It is a structural schematic diagram of an electronic device disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0034] This specific implementation manner is merely an explanation of an embodiment of the present invention, and it is not a limitation of the embodiment of the present invention. After reading this specification, a person skilled in the art may make non-creative modifications to the embodiment as needed, but as long as it is within the scope of the claims of the embodiment of the present invention, it is protected by the patent law.

[0035] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of them. Based on the embodiments in the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the embodiments of the present invention.

[0036] The term "comprise" and any variations thereof in the specification and claims of the present application are intended to cover non-exclusive inclusions. For example, a process, method, system, product or apparatus comprising a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to these processes, methods, products or apparatuses.

[0037] In the embodiments of the present invention, words such as "exemplary" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0038] The method of the present invention obtains the first environmental time series data of the laboratory in real time, preprocesses the environmental time series data, inputs the preprocessed second environmental time series data into a trained quantum kernel discriminant analysis model, and outputs the classification category of the second environmental time series data. It can effectively monitor the abnormality of the laboratory environmental data and avoid the abnormality of the laboratory environmental temperature and humidity affecting the accuracy of the experimental data.

[0039] The method of the present invention utilizes the characteristics of quantum states, and can accurately classify real-time environmental data even under small sample data. Compared with some traditional machine learning algorithms based on large data volume training, the method of the present invention can perform more effective feature extraction and analysis on small sample data through quantum kernel functions, so that reasonable classification of temperature and humidity can be achieved under small sample conditions. In addition, there are many complex factors in the laboratory environment that affect temperature and humidity, such as the diversity of experimental equipment, temperature and humidity changes caused by chemical reactions during the experiment, and the time when laboratory personnel frequently enter and exit or idle time. The method of the present invention can also encode these complex factors together with temperature and humidity data into quantum states, and comprehensively consider the interaction between these factors through quantum kernel functions, which is conducive to ensuring the suitability of the laboratory environment and abnormal processing of environmental data.

[0040] Embodiment 1

[0041] Please refer to Figure 1 As shown, a monitoring method for a laboratory environment intelligent adjustment system comprises the following steps:

[0042] Step S110: Acquire the first environment time series data of the laboratory in real time, and preprocess the first environment time series data to obtain the second environment time series data.

[0043] Wherein, the second environment time series data I=(I 1k ,I 2k ,...I ak ,...I n ), where I 1 is the environmental time series data of the first monitoring point at the kth time point, Ia is the environmental time series data of the ath monitoring point at the kth time point, In is the environmental time series data of the nth monitoring point at the kth time point, a and n are both natural numbers, k is the time point to which this moment belongs; the environmental time series data includes temperature and humidity data and experimental equipment operation data.

[0044] In this step, several monitoring points can be set in the laboratory, and sensors can be installed at each monitoring point to obtain the first environmental time series data. The location of the monitoring point can be adjusted according to the monitoring accuracy. For example, the installation location of the sensor can be optimized to avoid being directly affected by factors such as heat sources, water sources or vents, so as to improve the accuracy of data collection.

[0045] In a specific implementation, the k time point to which this moment belongs is related to the actual divided time interval. For example, when a month is divided into 30 days at equal time intervals, each day is divided into 12 time points.

[0046] In this step, the experimental equipment operation data may include data such as the name, quantity, power, and normal working conditions of the experimental equipment actually in operation.

[0047] Step S120: input the second environment time series data into the trained quantum kernel discriminant analysis model, output the classification category of the second environment time series data, the classification category includes three categories: suitable, relatively suitable and unsuitable, the quantum kernel discriminant analysis model encodes the second environment time series data to obtain new quantum state data, and then calculates the kernel matrix through the kernel function of the quantum kernel discriminant analysis model, obtains the similarity data of the quantum state through the kernel matrix, performs feature mapping on the similarity data, and then determines the projection position according to the mapping data after feature mapping and the projection direction, and outputs the category corresponding to the training data closest to the projection position in the projection space as the category of the second environment time series data; the projection direction is determined by solving the generalized eigenvalues ​​according to the intra-class divergence matrix Sw and the inter-class divergence matrix Sb of each category;

[0048] Specifically, the kernel function of the quantum kernel discriminant analysis model is Among them, x i is the environmental time series data of the ith monitoring point, x i is the environmental time series data of the jth monitoring point, K(x i ,x j ) is the similarity between the quantum state of the environmental time series data of the ith monitoring point and the quantum state of the environmental time series data of the jth monitoring point, γ is a constant, is the quantum state of the environmental time series data of the i-th monitoring point, is the quantum state of the environmental time series data of the jth monitoring point.

[0049] In a specific implementation, the quantum kernel discriminant analysis model is used to encode the second environment time series data to obtain new quantum state data, which can be encoded in the following manner:

[0050] For temperature and humidity data, the encoding method is selected according to the range and accuracy requirements of the temperature and humidity data. If the temperature and humidity data are within a smaller range and the accuracy requirements are higher, quantum amplitude encoding can be used. For example, the temperature range and humidity range are encoded into the amplitude of the quantum state at a certain resolution; for data containing time information (i.e., the moment when the temperature and humidity data are collected), the time can be encoded according to a certain period (such as hours, days), and together with the temperature and humidity data, a composite quantum state is formed. For example, the 24 hours of a day are divided into different time periods, and each time period is represented by the state of a quantum bit, which is combined with the quantum state of temperature and humidity.

[0051] In the specific implementation, the quantum kernel function is used to calculate the kernel matrix K. When the kernel function is a Gaussian kernel function, the generated kernel matrix is ​​a symmetric positive definite matrix. Since the laboratory temperature and humidity data are relatively small in scale, but the characteristic dimension may be high, the laboratory's computing resources can be fully utilized for efficient calculation when calculating the kernel matrix. For example, if the laboratory has a high-performance computer, parallel computing technology can be used to accelerate the calculation of the kernel matrix.

[0052] When implementing feature mapping, the original data is implicitly mapped to a high-dimensional quantum feature space through the kernel matrix. In this high-dimensional space, the complex relationship between temperature and humidity data and other related factors can be better reflected, which helps to explore the potential patterns in the data.

[0053] Among them, the inter-class scatter matrix S of each category B It measures the dispersion between different categories and is calculated as Among them, n c is the number of environmental time series data quantum states in the category, and μ is the mean vector of all environmental time series data quantum states (calculated in the quantum kernel space).

[0054] The intra-class scatter matrix Sw measures the degree of dispersion within each category and is obtained by calculating the difference between the quantum state data of the environmental time series data within each category and the mean vector of the category.

[0055] The projection direction is determined by solving the generalized eigenvalue of the intra-class scatter matrix Sw and the inter-class scatter matrix Sb of each class. Specifically, by solving the generalized eigenvalue problem To determine the projection direction, where α is the eigenvector and λ is the eigenvalue. Specifically, let M = S W -1 S B , then solve the eigenvalue λ and the corresponding eigenvector α of M, and then select the eigenvectors with the largest eigenvalues ​​as the projection direction, so that the distinction between different categories in the projected space is maximized. When outputting the category, the category corresponding to the training data closest to the projection position in the projection space is output as the category of the second environment time series data

[0056] Specifically, the quantum kernel discriminant analysis model is trained by the following method: obtaining the third environment time series data of each monitoring point running different numbers of experimental equipment at each time point as a training set, and training is performed using the third environment time series data, wherein the third environment time series data includes temperature and humidity data of a set number of experimental equipment in three categories of suitable, relatively suitable and unsuitable during operation, and the third environment time series data is feature mapped through a feature kernel matrix, and then the generalized eigenvalues ​​are solved according to the intra-class divergence matrix Sw and the inter-class divergence matrix Sb of each category to determine the projection direction, wherein the eigenvector corresponding to the maximum eigenvalue is used as the projection direction.

[0057] In this step, the environmental time series data includes temperature and humidity data, experimental equipment operation data and time information data. The third environmental time series data of each monitoring point at each time point is obtained by the following method:

[0058] A month is divided into m time points at equal time intervals, and the environmental data of each monitoring point at each time point when running different numbers of experimental equipment are obtained respectively, where m is a natural number. The environmental time series data of each monitoring point includes the environmental data at each time point, and the environmental data includes temperature and humidity data and experimental equipment operation data.

[0059] In this step, the time intervals can be divided according to months, days and Beijing time. For example, the temperature and humidity data of each hour in a laboratory for a month can be collected to form a data set. If a larger number of samples is required, the time intervals can be divided according to a year, for example, m = 365*24.

[0060] In the specific implementation, the training set data can be cleaned: for example, check whether there are missing values ​​or wrong values ​​in the training set data. If there is missing temperature and humidity data, it can be filled by linear interpolation and other methods according to the characteristics of the time series. For example, if the temperature data at a certain moment is missing, a reasonable estimate can be calculated based on the temperature values ​​before and after to fill it.

[0061] In the specific implementation, for each r value, the training set is used to train the quantum kernel discriminant analysis model, and then the prediction performance is evaluated on the validation set, and the value that minimizes the error on the validation set is selected as the final parameter.

[0062] For example, the fourth environment time series data for verification is obtained as a verification set, and the classification accuracy of the verification model on the verification set is verified to measure the accuracy between the predicted category error and the true category, and the r value with the highest classification accuracy is selected.

[0063] Step S3: when the second environment time series data is classified as unsuitable, the second environment time series data is recorded as abnormal data;

[0064] Step S4: Perform automatic adjustment according to the abnormal data.

[0065] As an embodiment, the step S4 may be performed by automatically adjusting the target adjustment strategy after determining it through an optimization algorithm.

[0066] In laboratory temperature and humidity regulation, the main goal of optimization calculation is to find the best adjustment strategy or equipment parameter settings so that the temperature and humidity of the laboratory can quickly and stably reach and maintain within the desired range. This is of great significance for ensuring the stability of the experimental environment, the accuracy of the experimental results, and the normal operation of the experimental equipment.

[0067] Specifically, they include:

[0068] Step S41: Obtain target adjustment data related to laboratory temperature and humidity adjustment.

[0069] In this step, the target data related to laboratory temperature and humidity regulation may include the status information and power of laboratory equipment during operation contained in the abnormal data, as well as the cooling capacity and heating capacity of air-conditioning equipment, the humidification capacity of humidifiers, the dehumidification capacity of dehumidifiers and other data.

[0070] Step S42: Classify the target adjustment data to obtain data sets corresponding to each level.

[0071] In this step, hierarchical data refers to the data related to the optimization process being divided into different levels or categories. For example, the first-level data may be data related to the basic characteristics of the temperature and humidity environment, such as the size of the laboratory space, the ventilation conditions of the doors and windows, the temperature and humidity contained in the abnormal data (as the initial temperature and humidity), etc.; the second-level data may be data related to the adjustment equipment, including the basic parameters of air conditioners, humidifiers, dehumidifiers and other equipment (such as power, maximum cooling / humidification / dehumidification capacity, etc.); the third-level data may be the intermediate results in the optimization process, such as the temperature and humidity deviations calculated in each iteration, the changes in the equipment adjustment parameters, etc.

[0072] Step S43: Perform hierarchical optimization calculations to obtain a target adjustment strategy, and adjust the temperature and humidity of the temperature and humidity adjustment device based on the target adjustment strategy.

[0073] In specific implementation, parameter combination tests can be performed through simple experiments or simulations based on experience. For example, first simulate the operation of different experimental equipment and the adjustment combination of temperature and humidity adjustment equipment in the laboratory to observe the changes in temperature and humidity. Use simple evaluation indicators, such as the time it takes for temperature and humidity to reach a comfortable range, the fluctuation range of temperature and humidity, etc. Based on the evaluation results, select those parameter range combinations that can make temperature and humidity relatively close to the comfortable range and have the fastest adjustment speed.

[0074] Assuming that after the first level of optimization, it is found that when the air conditioning temperature is set in the [22℃, 26℃] range, the humidifier working intensity is medium, and the dehumidifier working intensity is low, the temperature and humidity performance is relatively good, and the adjustment speed meets the preset time, then these ranges are determined as the basis for the second level of optimization.

[0075] Then, within the promising area determined at the first level, the optimal combination of adjustment parameters is found more accurately, so that the temperature and humidity in the laboratory can quickly and stably reach and be maintained within the appropriate temperature and humidity range and ensure that it is always within the appropriate temperature and humidity range. The optimal combination of adjustment parameters found is used as the target adjustment strategy.

[0076] Indicatively, taking two levels as an example, the parameter interval selected in the first level is further subdivided. For example, the air conditioning temperature adjustment setting interval [22℃, 26℃] is subdivided into [22℃, 23℃], [23℃, 24℃], [24℃, 25℃], and [25℃, 26℃]; for the working intensity of humidifiers and dehumidifiers, the medium intensity is further divided into three sub-levels: medium-low, medium, and medium-high. Then, a more accurate temperature and humidity simulation or experiment is performed to record the changes in temperature and humidity, and more accurate evaluation indicators are used, such as the sum of mean square errors (MSE) to measure the deviation of temperature and humidity from the center value of the comfort range (temperature is 22.5℃, relative humidity is 50%), and the deviation of the temperature and humidity adjustment time from the preset adjustment time threshold. Compare the evaluation indicators of all subdivided parameter combinations, and select the parameter combination that minimizes MSE as the optimal solution.

[0077] For example, after the second level of optimization, it is found that when the air conditioning temperature is set to 24°C, the humidifier working intensity is medium-high, and the dehumidifier working intensity is low-medium, the preset MSE is the smallest. This combination is the final temperature and humidity adjustment parameter combination.

[0078] In specific implementation, an optimization algorithm with low computational complexity can be selected, such as a simple gradient descent method or a simulated annealing algorithm, which have relatively low hardware requirements and can be run under limited resources, while also being able to meet the optimization requirements of temperature and humidity regulation to a certain extent.

[0079] As another embodiment, the step S4 may include:

[0080] The abnormal risk level is determined according to the abnormal data, and automatic adjustment is performed according to the abnormal risk level, wherein the abnormal risk level includes three levels: mild abnormality, moderate abnormality and severe abnormality.

[0081] Specifically, they include:

[0082] Step S411: Acquire the comfortable temperature and humidity data of the laboratory, determine that the abnormal data deviates from the comfortable temperature and humidity data by more than or equal to the first deviation data as a mild abnormality, determine that the abnormal data deviates from the comfortable temperature and humidity data by more than or equal to the second deviation data as a moderate abnormality, and determine that the abnormal data deviates from the comfortable temperature and humidity data by more than or equal to the third deviation data as a severe abnormality;

[0083] In this step, the comfortable temperature and humidity data and the deviation data can be set according to the actual situation.

[0084] For example, when the temperature exceeds the comfortable temperature and humidity data by 3-5°C and the humidity deviates from the set range by 15%-25%, the humidity reaches 80% or 25%, and the temperature reaches 30°C or 15°C, it is judged as moderate abnormality.

[0085] For example, if the temperature exceeds the set range by more than 5°C, the temperature reaches above 35°C or below 10°C, the humidity deviates from the set range by more than 25%, or the humidity reaches above 90% or below 15%, it is judged as a serious abnormality.

[0086] Step S412: When a mild abnormality or a moderate abnormality occurs, the temperature and humidity control equipment is adjusted; when a severe abnormality occurs, the temperature and humidity control equipment is adjusted at the same time, and the experimental equipment that meets the preset conditions is closed according to the experimental equipment operation data.

[0087] When serious anomalies occur, experimental equipment may malfunction or be damaged. For example, high-precision electronic equipment may burn out due to overheating, and some temperature-sensitive mechanical devices may freeze due to low temperatures and fail to operate normally.

[0088] In specific implementation, when mild and moderate abnormalities occur, the temperature and humidity of the laboratory can be adjusted through temperature and humidity adjustment equipment such as air conditioners and dehumidifiers / humidifiers. When serious abnormalities occur, when shutting down experimental equipment that meets the preset conditions, the preset conditions can comprehensively consider the name, quantity, power, necessity of opening the experimental equipment, and other data of the actual operating experimental equipment, so that the temperature and humidity of the laboratory can be restored to suitability as soon as possible.

[0089] Embodiment 2

[0090] The embodiment of the present invention discloses a laboratory environment intelligent adjustment system, such as Figure 2 As shown, Figure 2 It is an intelligent laboratory environment adjustment system, including:

[0091] The data acquisition unit 210 is used to obtain the first environment time series data of the laboratory in real time, and pre-process the first environment time series data to obtain the second environment time series data, wherein the second environment time series data I=(I 1 ,I 2,...Ia,...In), where, I 1 is the environmental time series data of the first monitoring point, Ia is the environmental time series data of the a-th monitoring point, In is the environmental time series data of the n-th monitoring point, and a and n are both natural numbers;

[0092] An analysis unit 220 is used to input the second environment time series data into a trained quantum kernel discriminant analysis model, and output classification categories of the second environment time series data, wherein the classification categories include three categories: suitable, relatively suitable, and unsuitable;

[0093] A recording unit 230, configured to record the second environment time series data as abnormal data when the classification category of the second environment time series data is inappropriate;

[0094] The adjustment unit 240 is configured to perform automatic adjustment according to the abnormal data.

[0095] Furthermore, the adjustment unit 240 includes:

[0096] A determination unit, configured to determine an abnormal risk level according to the abnormal data, and perform automatic adjustment according to the abnormal risk level, wherein the abnormal risk level includes three levels: mild abnormality, moderate abnormality, and severe abnormality;

[0097] The control unit is used to adjust the air conditioning equipment and dehumidifier when mild and moderate abnormalities occur, and to shut down the experimental equipment that meets the preset conditions according to the experimental equipment operation data when serious abnormalities occur.

[0098] In the specific implementation, sensor modules are set up at various monitoring points for collection. For example, high-precision temperature and humidity sensors are installed at different key locations in the laboratory to collect temperature and humidity data of the environment in real time.

[0099] In specific implementation, these sensor modules can accurately convert the physical quantity of the environment into electrical signals or digital signals. For example, using digital temperature and humidity sensors such as DHT11, it can directly output digital signals, which is convenient for communication with the control device.

[0100] When abnormal data occurs, the temperature and humidity adjustment operation is performed according to the instruction. For example, the temperature and humidity are adjusted by including but not limited to air conditioning systems, humidifiers, dehumidifiers, etc. Specifically, for air conditioning systems, the temperature can be adjusted by controlling its power switch, temperature setting value, wind speed and other parameters; for humidifiers and dehumidifiers, the humidity can be adjusted by controlling their working modes (such as humidification amount, dehumidification amount).

[0101] Specifically, temperature adjustment: If the temperature is high, send a signal to turn on the air conditioner's cooling mode, and adjust the air conditioner's set temperature and wind speed according to the size of the temperature deviation. If the temperature is low, turn on the air conditioner's heating mode or other heating equipment. For example, when the temperature deviation is large, adjust the air conditioner's wind speed to high gear to speed up the temperature adjustment.

[0102] Humidity adjustment: When the humidity is high, turn on the dehumidifier and control the working intensity of the dehumidifier according to the humidity deviation. If the humidity is low, turn on the humidifier. At the same time, the working time of the humidifier or dehumidifier can be dynamically adjusted according to the rate of humidity change to avoid excessive humidity adjustment.

[0103] In the specific implementation, a simple user interface can be developed to facilitate users to view temperature and humidity data and system status. In the specific implementation, an LCD display can be used to display temperature and humidity data and the working status of the equipment. If remote monitoring is required, the temperature and humidity data can be sent to the server or cloud platform through network programming, and users can remotely view and control the laboratory temperature and humidity control system through mobile phone applications or web browsers.

[0104] Embodiment 3

[0105] See also Figure 3 , Figure 3 Schematic diagram of the structure of an electronic device disclosed in an embodiment of the present invention. Figure 3 As shown, the electronic device may include:

[0106] A memory 310 storing executable program codes;

[0107] a processor 320 coupled to the memory 310;

[0108] The processor 320 calls the executable program code stored in the memory 310 to execute part or all of the steps in the monitoring method of the laboratory environment intelligent adjustment system in the first embodiment.

[0109] An embodiment of the present invention discloses a computer-readable storage medium storing a computer program, wherein the computer program enables a computer to execute part or all of the steps in a monitoring method of a laboratory environment intelligent adjustment system in embodiment one.

[0110] The embodiment of the present invention further discloses a computer program product, wherein when the computer program product is run on a computer, the computer is enabled to execute part or all of the steps in the monitoring method of a laboratory environment intelligent adjustment system in the first embodiment.

[0111] An embodiment of the present invention also discloses an application publishing platform, wherein the application publishing platform is used to publish a computer program product, wherein when the computer program product runs on a computer, the computer executes part or all of the steps in a monitoring method of a laboratory environment intelligent adjustment system in embodiment one.

[0112] In various embodiments of the present invention, it should be understood that the size of the serial numbers of the processes does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0113] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, i.e., they may be located in one place or distributed over multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0114] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0115] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-accessible memory. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product, which is stored in a memory and includes several requests for a computer device (which can be a personal computer, a server or a network device, etc., specifically a processor in a computer device) to perform some or all of the steps of the method described in each embodiment of the present invention.

[0116] In the embodiments provided by the present invention, it should be understood that "B corresponding to A" means that B is associated with A, and B can be determined according to A. However, it should also be understood that determining B according to A does not mean determining B only according to A, and B can also be determined according to A and / or other information.

[0117] A person of ordinary skill in the art can understand that some or all of the steps in the various methods of the embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium, and the storage medium includes a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable programmable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0118] The monitoring method, device, electronic device and storage medium of a laboratory environment intelligent adjustment system disclosed in an embodiment of the present invention are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for general technical personnel in this field, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A laboratory environment intelligent adjustment system, characterized in that: It includes the following: A data acquisition unit is used to acquire the first environmental time series data of the laboratory in real time, and preprocess the first environmental time series data to obtain second environmental time series data, wherein the second environmental time series data I=(I1, I2, ... Ia, ... In), wherein I1 is the environmental time series data of the first monitoring point, Ia is the environmental time series data of the a-th monitoring point, In is the environmental time series data of the n-th monitoring point, and a and n are both natural numbers; An analysis unit, used for inputting the second environment time series data into a trained quantum nuclear discriminant analysis model, and outputting classification categories of the second environment time series data, wherein the classification categories include three categories: suitable, relatively suitable, and unsuitable; A recording unit, configured to record the second environment time series data as abnormal data when the classification category of the second environment time series data is inappropriate; An adjustment unit is used to perform automatic adjustment according to the abnormal data.

2. The laboratory environment intelligent adjustment system according to claim 1, characterized in that: The adjustment unit comprises: A determination unit, configured to determine an abnormal risk level according to the abnormal data, and perform automatic adjustment according to the abnormal risk level, wherein the abnormal risk level includes three levels: mild abnormality, moderate abnormality, and severe abnormality; The control unit is used to adjust the air conditioning equipment and dehumidifier when mild and moderate abnormalities occur, and to shut down the experimental equipment that meets the preset conditions according to the experimental equipment operation data when serious abnormalities occur.

3. A monitoring method for a laboratory environment intelligent adjustment system, characterized in that: It includes the following steps: Acquire the first environmental time series data of the laboratory in real time, and preprocess the first environmental time series data to obtain the second environmental time series data, wherein the second environmental time series data I=(I1, I2, ... Ia, ... In), wherein I1 is the environmental time series data of the first monitoring point, Ia is the environmental time series data of the a-th monitoring point, In is the environmental time series data of the n-th monitoring point, and a and n are both natural numbers; Inputting the second environmental time series data into the trained quantum kernel discriminant analysis model, and outputting the classification categories of the second environmental time series data, wherein the classification categories include three categories: suitable, relatively suitable, and unsuitable; When the classification category of the second environment time series data is inappropriate, the second environment time series data is recorded as abnormal data; Automatic adjustment is performed based on the abnormal data.

4. The monitoring method of the laboratory environment intelligent adjustment system according to claim 3 is characterized in that: Inputting the second environment time series data into the trained quantum kernel discriminant analysis model, and outputting the classification category of the second environment time series data, including: The quantum kernel discriminant analysis model encodes the second environment time series data to obtain new quantum state data, and then calculates the kernel matrix through the kernel function of the quantum kernel discriminant analysis model, obtains the similarity data of the quantum state through the kernel matrix, performs feature mapping on the similarity data, and then determines the projection position according to the mapping data after feature mapping and the projection direction, and outputs the category corresponding to the training data closest to the projection position in the projection space as the category of the second environment time series data; the projection direction is determined by solving the generalized eigenvalues ​​based on the intra-class divergence matrix Sw and the inter-class divergence matrix Sb of each category.

5. The monitoring method of the laboratory environment intelligent adjustment system according to claim 4 is characterized in that: Kernel function of the quantum kernel discriminant analysis model Among them, x i is the environmental time series data of the ith monitoring point, x i is the environmental time series data of the jth monitoring point, K(x i ,x j ) is the similarity between the quantum state of the environmental time series data of the ith monitoring point and the quantum state of the environmental time series data of the jth monitoring point, γ is a constant, is the quantum state of the environmental time series data of the i-th monitoring point, is the quantum state of the environmental time series data of the jth monitoring point.

6. The monitoring method of the laboratory environment intelligent adjustment system according to claim 3 is characterized in that: The quantum kernel discriminant analysis model is trained by the following method: The third environment time series data of each monitoring point running different numbers of experimental equipment at each time point is obtained as a training set, and training is performed using the third environment time series data. The time points divide a month into m time points at equal time intervals, where m is a natural number. The environment time series data includes temperature and humidity data, experimental equipment operation data, and time information data.

7. The monitoring method of the laboratory environment intelligent adjustment system according to claim 3 is characterized in that: The performing automatic adjustment according to the abnormal data includes: Determine the abnormal risk level according to the abnormal data, and perform automatic adjustment according to the abnormal risk level, wherein the abnormal risk level includes three levels: mild abnormality, moderate abnormality and severe abnormality; or, perform automatic adjustment after determining the target adjustment strategy through an optimization algorithm.

8. The monitoring method of the laboratory environment intelligent adjustment system according to claim 7, characterized in that: The determining the abnormal risk level according to the abnormal data includes: Obtain the comfortable temperature and humidity data of the laboratory, and determine that the abnormal data deviates from the comfortable temperature and humidity data by more than or equal to the first deviation data as a mild abnormality, the abnormal data deviates from the comfortable temperature and humidity data by more than or equal to the second deviation data as a moderate abnormality, and the abnormal data deviates from the comfortable temperature and humidity data by more than or equal to the third deviation data as a severe abnormality.

9. An electronic device, characterized in that: It includes: a memory storing executable program code; a processor coupled to the memory; the processor calls the executable program code stored in the memory to execute the monitoring method of the laboratory environment intelligent adjustment system according to any one of claims 3-8.

10. A computer-readable storage medium, characterized in that: It stores a computer program, wherein the computer program enables a computer to execute the monitoring method of the laboratory environment intelligent adjustment system as described in any one of claims 3-8.

Images