Sample drying device and method for environmental monitoring laboratory
By collecting multi-point humidity data and near-infrared spectral information in the environmental monitoring laboratory and conducting entropy weight fusion evaluation, the problem of inaccurate water content evaluation in traditional drying technology is solved, and the drying control accuracy and experimental data are improved. reliability.
Patent Information
- Application Number
- CN202411400965.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-09
- Publication Date
- 2024-12-27
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Traditional drying technology is difficult to achieve accurate assessment of sample moisture content in environmental monitoring laboratories, resulting in insufficient drying control accuracy and affecting the accuracy and reliability of experimental results.
By collecting humidity data from multiple monitoring points in the enclosed drying space, determining the confidence distance and humidity dependence, extracting humidity characteristics and sensor mutual interference coefficients, combining near-infrared spectral information for trend extrapolation, and performing entropy weight fusion evaluation to improve Control accuracy of sample drying process.
Multi-point fusion confidence evaluation of sample water content is achieved, sensor mutual interference error is eliminated, humidity gradient changes are accurately captured, insufficient drying or excessive drying is avoided, and the reliability and accuracy of experimental data are improved.
Smart Images
Figure CN119198250A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of drying equipment, and more specifically, to a sample drying device and method for an environmental monitoring laboratory. Background Art
[0002] Drying equipment is a device used to remove moisture from samples or materials. It is widely used in industrial production, laboratory research, food processing, agriculture and other fields. It mainly evaporates and discharges the moisture in the material through heating, air circulation and humidity control to achieve the purpose of drying. Common drying equipment includes hot air dryers, vacuum dryers and freeze dryers, etc., which are suitable for different types of materials and drying needs. These equipment play a key role in various fields, helping to optimize the production process, preserve product quality, and support precision laboratory research.
[0003] In the existing technology, by monitoring and analyzing the moisture content of the sample, the drying conditions can be adjusted in time to avoid excessive or insufficient drying and reduce losses, thereby ensuring sample quality, optimizing the drying process and improving resource utilization efficiency. However, traditional sample drying technology faces many challenges in environmental monitoring laboratories, especially the difficulty in accurately evaluating the moisture content of environmental monitoring laboratory samples. Traditional drying technology usually relies on a single humidity sensor or simple timing control, which can easily lead to a large number of errors in the moisture content evaluation of laboratory samples. Since the humidity distribution of laboratory samples is uneven during the drying process, and a single sensor cannot fully capture the humidity changes in the entire space, the drying degree of various parts of the laboratory samples is inconsistent. In addition, the existence of humidity changes on the surface of laboratory samples further exacerbates the accuracy of moisture content. The difficulty of accurate evaluation, especially when the surface moisture content of laboratory samples varies greatly, traditional methods are difficult to capture these subtle changes, resulting in insufficient drying control precision, which in turn affects the accuracy of experimental results. This lack of control precision not only leads to insufficient or excessive drying of laboratory samples, affecting the reliability of experimental data, but also brings unforeseen errors to subsequent experimental data analysis and processing. By performing multi-point coupled confidence evaluation on the moisture content of laboratory samples in environmental monitoring, it can effectively make up for the limitations of traditional laboratory sample drying technology that is difficult to meet the requirements of modern environmental monitoring laboratories for high-precision and high-reliability laboratory sample processing. Therefore, how to achieve multi-point fusion confidence evaluation of the moisture content of laboratory samples, thereby improving the control accuracy of the sample drying process has become a difficult problem faced by the industry. Summary of the invention
[0004] The present application provides a sample drying device and method for an environmental monitoring laboratory, which can realize multi-point fusion confidence evaluation of the moisture content of laboratory samples, thereby improving the control accuracy of the sample drying process.
[0005] In a first aspect, the present application provides a method for evaluating the moisture content of a laboratory sample, which is used in an environmental monitoring laboratory to evaluate the moisture content of a laboratory sample using a sample drying device, the method comprising:
[0006] Collect the humidity of the target laboratory sample at multiple monitoring points in the closed drying space to obtain space humidity data;
[0007] Determine the confidence distance between each monitoring point, and perform dependency association on the humidity difference in the spatial humidity data through each confidence distance to obtain the humidity dependency relationship between all monitoring points;
[0008] Extracting humidity characteristics at each monitoring point from the spatial humidity data, determining the mutual interference coefficients of sensors between the monitoring points according to all humidity characteristics and the humidity dependency, and then coupling mapping the moisture content of the closed drying space based on all mutual interference coefficients and the spatial humidity data to obtain the spatial moisture content;
[0009] Acquire near-infrared spectrum information of the surface of the target laboratory sample, perform trend extrapolation on the water content of the surface of the target laboratory sample based on the water molecule characterization spectrum in the near-infrared spectrum information, obtain an extrapolation curve of the surface water content, and then determine the surface water content of the target laboratory sample according to the extrapolation curve;
[0010] The moisture content of the target laboratory sample is evaluated by entropy weight fusion based on the spatial moisture content and the surface moisture content to obtain an evaluation value of the moisture content of the target laboratory sample.
[0011] Preferably, determining the confidence distance between each monitoring point specifically includes:
[0012] Obtain the humidity data at each monitoring point, and then determine the trend similarity of humidity changes between each monitoring point based on all humidity data;
[0013] The confidence distance between each monitoring point is determined by the distance between each monitoring point and all trend similarities.
[0014] Preferably, performing dependency association on the humidity differences in the spatial humidity data through each confidence distance to obtain the humidity dependency relationship between all monitoring points specifically includes:
[0015] Extracting humidity differences between various monitoring points from the spatial humidity data;
[0016] Select two monitoring points as the selected monitoring label pair;
[0017] Obtain the confidence distance between the monitoring points of the selected monitoring tag pair;
[0018] Determine the correlation dependency value between the monitoring points in the selected monitoring tag pair through all humidity differences and the confidence distances between the monitoring points in the selected monitoring tag pair;
[0019] Continue to determine the association dependency values between the monitoring points in the remaining monitoring tag pairs;
[0020] The dependency matrix composed of all associated dependency values is used as the humidity dependency relationship between all monitoring points.
[0021] Preferably, extracting the humidity characteristics at each monitoring point from the spatial humidity data specifically includes:
[0022] Extracting humidity data at each monitoring point from the spatial humidity data;
[0023] The humidity data at each monitoring point are subjected to characteristic regression fitting to obtain the humidity characteristics at each monitoring point.
[0024] Preferably, determining the mutual interference coefficient of sensors between various monitoring points according to all humidity characteristics and the humidity dependency specifically includes:
[0025] Select two monitoring points as the selected monitoring label pair;
[0026] Obtaining the associated dependency value between the monitoring points in the selected monitoring tag pair from the humidity dependency relationship;
[0027] Determine the mutual support of humidity characteristics between monitoring points in the selected monitoring tag pairs;
[0028] Determine the mutual interference coefficient of sensors between monitoring points in the selected monitoring tag pair through the mutual support and the associated dependency value;
[0029] Continue to determine the mutual interference coefficients of sensors between monitoring points in the remaining monitoring tag pairs.
[0030] Preferably, coupling mapping is performed on the moisture content of the enclosed drying space based on all the mutual interference coefficients and the spatial humidity data to obtain the spatial moisture content, which specifically includes:
[0031] The spatial humidity data is coupled and corrected by all the mutual interference coefficients to obtain corrected humidity data;
[0032] Mapping the corrected humidity data into the moisture content of each monitoring point;
[0033] A spatial interpolation operation is performed on the moisture content of each monitoring point to obtain a moisture content distribution curve of the closed drying space, and then the spatial moisture content of the closed drying space is extracted from the moisture content distribution curve.
[0034] Preferably, the sensor is a humidity sensor.
[0035] In a second aspect, the present application provides a sample drying device for an environmental monitoring laboratory, the sample drying device for an environmental monitoring laboratory comprising a moisture content evaluation unit, the moisture content evaluation unit comprising:
[0036] A collection module is used to collect the humidity of target laboratory samples at multiple monitoring points in a closed drying space in real time to obtain space humidity data;
[0037] A processing module, used to determine the confidence distance between each monitoring point, and to perform dependency association on the humidity difference in the spatial humidity data through each confidence distance to obtain the humidity dependency relationship between all monitoring points;
[0038] The processing module is further used to extract humidity characteristics at each monitoring point from the spatial humidity data, determine the mutual interference coefficients of sensors between the monitoring points according to all humidity characteristics and the humidity dependency, and then perform coupling mapping on the moisture content of the closed drying space based on all mutual interference coefficients and the spatial humidity data to obtain the spatial moisture content;
[0039] The processing module is further used to obtain near-infrared spectrum information of the surface of the target laboratory sample, perform trend extrapolation on the water content of the surface of the target laboratory sample from the water molecule characterization spectrum in the near-infrared spectrum information, obtain an extrapolation curve of the surface water content, and then determine the surface water content of the target laboratory sample according to the extrapolation curve;
[0040] An execution module is used to perform entropy weight fusion evaluation on the moisture content of the target laboratory sample based on the spatial moisture content and the surface moisture content to obtain an evaluation value of the moisture content of the target laboratory sample.
[0041] In a third aspect, the present application provides a computer device, comprising a memory and a processor, wherein the memory stores codes, and the processor is configured to obtain the codes and execute the above-mentioned method for assessing the moisture content of laboratory samples.
[0042] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned method for evaluating the moisture content of a laboratory sample is implemented.
[0043] The technical solution provided by the embodiments disclosed in this application has the following beneficial effects:
[0044] In an embodiment of the present application, the humidity of a target laboratory sample at multiple monitoring points in a closed drying space is collected to obtain spatial humidity data; the confidence distance between each monitoring point is determined, and the humidity difference in the spatial humidity data is dependently associated through each confidence distance to obtain the humidity dependency relationship between all monitoring points; the humidity characteristics at each monitoring point are extracted from the spatial humidity data, and the mutual interference coefficient of the sensors between each monitoring point is determined based on all the humidity characteristics and the humidity dependency relationship, and then the moisture content of the closed drying space is coupled and mapped based on all the mutual interference coefficients and the spatial humidity data to obtain the spatial moisture content; the near-infrared spectral information of the surface of the target laboratory sample is obtained, and the moisture content of the surface of the target laboratory sample is trend extrapolated by the water molecule characterization spectrum in the near-infrared spectral information to obtain an extrapolation curve of the surface moisture content, and then the surface moisture content of the target laboratory sample is determined according to the extrapolation curve; the moisture content of the target laboratory sample is evaluated by entropy weight fusion based on the spatial moisture content and the surface moisture content to obtain an evaluation value of the moisture content of the target laboratory sample.
[0045] It can be seen that the present application performs entropy weight fusion evaluation on the moisture content of the target laboratory sample through spatial moisture content and surface moisture content to obtain the moisture content evaluation value of the target laboratory sample; wherein, firstly, multiple monitoring points are arranged in a closed drying space and humidity data is collected in real time, which can comprehensively capture the changes in spatial humidity, thereby improving the monitoring accuracy of moisture content during the laboratory sample drying process; secondly, by quantifying the mutual interference coefficient between sensors, the measurement error caused by the mutual interference effect of sensors can be eliminated, thereby improving the accuracy of humidity measurement, and then the mutual interference coefficient between sensors and the spatial humidity data are coupled and mapped to the moisture content of the closed drying space to obtain the spatial moisture content, which can better describe the average distribution of moisture in the closed drying space, and then improve the precise control of laboratory samples in the drying process; then, the surface moisture content of the target laboratory sample is trend extrapolated by the water molecule characterization spectrum in the near-infrared spectral information to obtain the extrapolation curve of the surface moisture content, and the extrapolation curve is used to obtain the surface moisture content. The line can accurately capture the gradient change of the surface moisture content of the laboratory sample, and then calibrate the extrapolation curve through the wet basis moisture content, which improves the reliability of the extrapolation curve, thereby obtaining a more accurate surface moisture content. The surface moisture content can predict the moisture diffusion behavior of the laboratory sample during the drying process, thereby avoiding local over-drying of the laboratory sample; finally, based on the spatial moisture content and the surface moisture content, the moisture content of the target laboratory sample is evaluated by entropy weight fusion, and the moisture content evaluation value of the target laboratory sample is obtained. The moisture content evaluation value can comprehensively consider the changing trend of the moisture content on the surface of the laboratory sample and inside the closed drying space, and accurately evaluate the moisture content of the laboratory sample, which can avoid insufficient drying or local over-drying of the laboratory sample, thereby ensuring that the state of the laboratory sample during the drying process is always in the optimal state, thereby improving the reliability and accuracy of the experimental data; in summary, the present application scheme can realize multi-point fusion confidence evaluation of the moisture content of laboratory samples, thereby improving the control accuracy of the sample drying process. BRIEF DESCRIPTION OF THE DRAWINGS
[0046] Figure 1 is an exemplary flow chart of a method for evaluating the moisture content of a laboratory sample according to some embodiments of the present application;
[0047] Figure 2 is a schematic diagram of a process for determining a mutual interference coefficient according to some embodiments of the present application;
[0048] Figure 3 is a schematic diagram of a process for determining surface water content according to some embodiments of the present application;
[0049] Figure 4 is a schematic diagram of an exemplary software module of a water content evaluation unit according to some embodiments of the present application;
[0050] Figure 5 It is a schematic diagram of the structure of a computer device according to a method for evaluating the moisture content of a laboratory sample as shown in some embodiments of the present application. DETAILED DESCRIPTION
[0051] The core of this application is to collect the humidity of the target laboratory sample at multiple monitoring points in a closed drying space to obtain spatial humidity data; determine the confidence distance between each monitoring point, and perform dependency association on the humidity difference in the spatial humidity data through each confidence distance to obtain the humidity dependency relationship between all monitoring points; extract the humidity characteristics at each monitoring point from the spatial humidity data, determine the mutual interference coefficient of the sensors between each monitoring point according to all humidity characteristics and the humidity dependency relationship, and then perform coupling mapping on the moisture content of the closed drying space based on all mutual interference coefficients and the spatial humidity data to obtain the spatial moisture content; obtain the near-infrared spectral information of the surface of the target laboratory sample, and perform trend extrapolation on the moisture content of the surface of the target laboratory sample by the water molecule characterization spectrum in the near-infrared spectral information to obtain the extrapolation curve of the surface moisture content, and then determine the surface moisture content of the target laboratory sample according to the extrapolation curve; perform entropy weight fusion evaluation on the moisture content of the target laboratory sample based on the spatial moisture content and the surface moisture content to obtain the moisture content evaluation value of the target laboratory sample. By adopting the scheme of the present application, a multi-point fusion confidence assessment of the moisture content of laboratory samples can be achieved, thereby improving the control accuracy of the sample drying process.
[0052] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods. Figure 1 , which is an exemplary flow chart of a method for evaluating the moisture content of a laboratory sample according to some embodiments of the present application. The method 100 for evaluating the moisture content of a laboratory sample mainly includes the following steps:
[0053] In step 101, the humidity of a target laboratory sample at multiple monitoring points in a closed drying space is collected to obtain space humidity data.
[0054] In specific implementation, the laboratory samples to be dried are spread out in a sample drying device for an environmental monitoring laboratory, and the sample drying device is started. The working parameters of the drying process are collected through sensors in the sample drying device, and the collected working parameters are stored in a database. The humidity of the target laboratory samples at multiple monitoring points in a closed drying space can then be obtained from the database, and a set of humidity data collected at all monitoring points is used as space humidity data. It should be noted that in this application, humidity data is collected once every 1 second, and the collection time is also set to 1 second. In other embodiments, the collection interval time can also be set to other interval time. The smaller the interval, the closer the dehumidification effect of the sample drying device is to the ideal state. The specific interval time is not limited here.
[0055] It should be noted that when the sample drying device for the environmental monitoring laboratory is started, the sensor starts collecting data and does not stop collecting data until the sample drying device for the environmental monitoring laboratory stops drying. It should also be noted that the humidity data in this application refers to the set of humidity values collected from the current moment to the start of the sample drying device for the environmental monitoring laboratory; it should also be noted that the sensor in this application is a humidity sensor. In addition, the sampling frequency of the sensor can be set between 100Hz-200Hz, and can also be set in other ranges in other embodiments, which is not limited here.
[0056] In step 102, the confidence distances between the various monitoring points are determined, and the humidity differences in the spatial humidity data are subjected to dependency association through the various confidence distances to obtain the humidity dependency relationship between all the monitoring points.
[0057] In some embodiments, determining the confidence distance between each monitoring point may be achieved by using the following steps:
[0058] Obtain the humidity data at each monitoring point, and then determine the trend similarity of humidity changes between each monitoring point based on all humidity data;
[0059] The confidence distance between each monitoring point is determined by the distance between each monitoring point and all trend similarities.
[0060] In the specific implementation, it should be noted that the trend similarity in the present application is an indicator for measuring the similarity of the trend of humidity data changes between monitoring points. Specifically, the trend similarity of humidity changes between each monitoring point determined based on all humidity data can be implemented in the following manner, namely: the cosine similarity between the corresponding humidity data of any two monitoring points can be used as the trend similarity of humidity changes between the two monitoring points; the confidence distance between each monitoring point determined by the distance between each monitoring point and all trend similarities can be implemented in the following manner, namely: two monitoring points are selected as the selected monitoring group, and the distance and trend similarity between the monitoring points in the selected monitoring group are obtained. The weighted sum of the distance and the trend similarity can be used as the confidence distance between the monitoring points in the selected monitoring group, wherein the weights of the distance and the trend similarity can be preset according to historical monitoring data. In the present application, the weights of the distance and the trend similarity are both set to 0.5, and then the confidence distance between the monitoring points in the remaining selected monitoring group is determined.
[0061] It should be noted that the confidence distance in this application is an indicator for quantifying the degree of correlation between two monitoring points. The larger the confidence distance, the weaker the correlation between the two monitoring points. By comprehensively considering the two factors of physical space distance and trend similarity, the description accuracy of the degree of correlation between monitoring points can be improved, thereby making the confidence distance closer to reality.
[0062] In some embodiments, the humidity differences in the spatial humidity data are subjected to dependency association through each confidence distance, and the humidity dependency relationship between all monitoring points can be obtained by the following steps:
[0063] Extracting humidity differences between various monitoring points from the spatial humidity data;
[0064] Select two monitoring points as the selected monitoring label pair;
[0065] Obtain the confidence distance between the monitoring points of the selected monitoring tag pair;
[0066] Determine the correlation dependency value between the monitoring points in the selected monitoring tag pair through all humidity differences and the confidence distances between the monitoring points in the selected monitoring tag pair;
[0067] Continue to determine the association dependency values between the monitoring points in the remaining monitoring tag pairs;
[0068] The dependency matrix composed of all associated dependency values is used as the humidity dependency relationship between all monitoring points.
[0069] In the specific implementation, first, the humidity data of each monitoring point is obtained from the spatial humidity data, and then the Euclidean distance of the humidity data between any two monitoring points is used as the humidity difference; secondly, two monitoring points are arbitrarily selected from all the monitoring points as the selected monitoring label pair, wherein the selected monitoring label pair represents a combination of two monitoring points, and then the confidence distance between the monitoring points in the selected monitoring label pair is obtained; then, the largest humidity difference is selected from all the humidity differences, and the largest humidity difference is used as the maximum difference value, and then the sum of the confidence distance and the constant 1 is used as the confidence sum, and the confidence sum is usually used as the denominator, and its role is to ensure the numerator ratio The denominator is large, and then the ratio of the humidity difference between the monitoring points in the selected monitoring tag pair to the maximum difference value is taken as the maximum difference ratio, and then the difference between the constant 1 and the maximum difference ratio can be taken as the relative difference value, and further, the product of the reciprocal of the confidence sum and the relative difference value can be taken as the correlation dependency value of the humidity between the monitoring points in the selected monitoring tag pair, and then the correlation dependency values between the monitoring points in the remaining monitoring tag pairs are further obtained; finally, all the correlation dependency values are combined according to the distribution position information of the corresponding monitoring points, and the combined dependency matrix is taken as the humidity dependency relationship between all monitoring points, wherein each element R in the dependency matrix ij Indicates monitoring point P i and P j The dependency matrix can be used for subsequent humidity data analysis and processing.
[0070] It should be noted that the correlation dependency value in this application is an indicator for measuring the degree of correlation dependency between monitoring points; in addition, the dependency matrix is a comprehensive description of the degree of dependency between all monitoring points. It can intuitively display the correlation between monitoring points and provide a basis for subsequent analysis, prediction and system optimization, where the elements of the dependency matrix represent the dependency strength between corresponding monitoring label pairs (two monitoring points); it should also be noted that the humidity dependency relationship between all monitoring points describes the overall correlation between the monitoring points, especially the correlation effect of humidity changes at one monitoring point on another monitoring point. The main function of the humidity dependency relationship is to help understand and analyze the mutual influence between the monitoring points in the system. By clarifying the humidity dependency relationship between monitoring points, the layout of the monitoring system can be optimized, the accuracy of data integration can be improved, and the reliability of the moisture content prediction model can be enhanced.
[0071] In step 103, the humidity characteristics at each monitoring point are extracted from the spatial humidity data, and the mutual interference coefficients of the sensors between the monitoring points are determined based on all the humidity characteristics and the humidity dependency. Then, the moisture content of the enclosed drying space is coupled and mapped based on all the mutual interference coefficients and the spatial humidity data to obtain the spatial moisture content.
[0072] In some embodiments, the extraction of humidity characteristics at each monitoring point from the spatial humidity data may be achieved by using the following steps:
[0073] Extracting humidity data at each monitoring point from the spatial humidity data;
[0074] The humidity data at each monitoring point are subjected to characteristic regression fitting to obtain the humidity characteristics at each monitoring point.
[0075] In specific implementation, first, the humidity data at each monitoring point can be intercepted from the spatial humidity data, and then the humidity data at each monitoring point can be used as the initialization parameter of the pre-trained regression model, and then the humidity data at each monitoring point can be subjected to feature regression fitting through the regression model, so that the multiple humidity values obtained by regression fitting can be used as the humidity features at the corresponding monitoring points. In other embodiments, the average value of the humidity data at the monitoring point can also be used as the humidity feature. In the present application, the humidity data of the monitoring point is used to regress and predict the humidity feature at the monitoring point. Compared with using the average value of the humidity data as the humidity feature, the influence of abnormal values on the humidity feature can be reduced, thereby improving the accuracy of the humidity feature.
[0076] It should be noted that the pre-trained regression model in the present application can be implemented based on a decision tree regression algorithm, and other algorithms can also be used in other embodiments. The overall regression characteristics of the humidity data can be analyzed through the regression model, thereby improving the robustness of the humidity characteristics; it should also be noted that the pre-trained regression model can be obtained by training with a large amount of humidity data.
[0077] In some embodiments, reference Figure 2 As shown, this figure is a schematic diagram of the process of determining the mutual interference coefficient in some embodiments of the present application. In this embodiment, the mutual interference coefficient of the sensors between each monitoring point is determined according to all humidity characteristics and the humidity dependency relationship, which can be implemented by the following steps:
[0078] In step 1031, two monitoring points are selected as selected monitoring tag pairs;
[0079] In step 1032, the correlation dependency value between the monitoring points in the selected monitoring tag pair is obtained from the humidity dependency relationship;
[0080] In step 1033, the mutual support of humidity characteristics between monitoring points in the selected monitoring tag pair is determined;
[0081] In step 1034, the mutual interference coefficient of the sensors between the monitoring points in the selected monitoring tag pair is determined by the mutual support and the associated dependency value;
[0082] In step 1035, the mutual interference coefficients of the sensors between the monitoring points of the remaining monitoring tag pairs continue to be determined.
[0083] In the specific implementation, first, any two monitoring points are selected from all the monitoring points as the selected monitoring tag pair, and then the associated dependency value between the monitoring points in the selected monitoring tag pair is screened out from the humidity dependency relationship; then, the similarity of the humidity characteristics between the monitoring points in the selected monitoring tag pair can be used as the mutual support of the humidity characteristics between the monitoring points in the selected monitoring tag pair, wherein the similarity can be described by the Euclidean distance in the prior art. In other embodiments, other methods can also be used to describe the similarity, which is not limited here; thirdly, the product of the associated dependency value and the mutual support can be used as the target dependency value, and the difference between the associated dependency value and the target dependency value can be used as the mutual interference residual between the sensors, and then the ratio of the mutual interference residual to the mutual support can be used as the mutual interference coefficient of the sensors between the monitoring points in the selected monitoring tag pair, and further, the mutual interference coefficient of the sensors between the monitoring points in the remaining monitoring tag pairs can be obtained.
[0084] It should be noted that the mutual support in the present application is an indicator for measuring the similarity of humidity characteristics between monitoring points. The higher the mutual support, the higher the similarity of humidity characteristics between monitoring points. The lower the mutual support, the lower the similarity of humidity characteristics between monitoring points. It should also be noted that the mutual interference coefficient is an indicator for measuring the strength of mutual interference effect between sensors. By quantifying the strength of mutual interference effect between sensors, the collected humidity data can be corrected, thereby reducing the interference of the monitoring environment on the moisture content test, which is beneficial to improving the accuracy of control parameters during the drying process. Among them, the sensor is a humidity sensor, and other types of sensors can also be used in specific implementation, without specific limitation here.
[0085] In some embodiments, coupling mapping is performed on the moisture content of the enclosed drying space based on all the mutual interference coefficients and the spatial humidity data to obtain the spatial moisture content, which can be achieved by the following steps:
[0086] The spatial humidity data is coupled and corrected by all the mutual interference coefficients to obtain corrected humidity data;
[0087] Mapping the corrected humidity data into the moisture content of each monitoring point;
[0088] A spatial interpolation operation is performed on the moisture content of each monitoring point to obtain a moisture content distribution curve of the closed drying space, and then the spatial moisture content of the closed drying space is extracted from the moisture content distribution curve.
[0089] In specific implementation, the spatial humidity data is coupled and corrected by all the mutual interference coefficients to obtain the corrected humidity data, which can be achieved in the following manner, namely: a data correction model can be initialized first, and all the mutual interference coefficients are used as constraint parameters of the data correction model, and the humidity data at each monitoring point in the spatial humidity data is used as the input parameter of the data correction model, and then the corrected humidity data is output through the data correction model, wherein the intensity of the mutual interference effect between sensors can be judged by the size of the mutual interference coefficient in the constraint parameter, and when the mutual interference coefficient is greater than the threshold, it is necessary to correct the humidity data of the sensor corresponding to the mutual interference coefficient, for example, the interference effect between sensors can be eliminated through a mathematical model; it should be noted that the algorithm structure in the data correction model in the present application can adopt a convolutional neural network, and in other embodiments, other algorithm structures can also be adopted, which are not limited here.
[0090] In addition, the mapping of the corrected humidity data into the moisture content of each monitoring point can be achieved in the following manner, namely: the corrected humidity data corresponding to each monitoring point in the corrected humidity data can be substituted into the existing humidity-moisture content empirical formula, and then the mapping result is used as the moisture content of each monitoring point; the spatial interpolation operation is performed on the moisture content of each monitoring point, and the moisture content distribution curve of the closed drying space can be obtained in the following manner, namely: the Kriging interpolation method in the prior art can be used to interpolate the moisture content of the space where each monitoring point is located, so as to analyze the distribution of moisture content in the entire closed drying space, and then the moisture content of all the monitoring points in the closed drying space can be interpolated. The three-dimensional curve composed of moisture content is used as the moisture distribution curve of the closed drying space; the spatial moisture content of the closed drying space can be extracted from the moisture distribution curve in the following manner, namely: all moisture contents in the moisture distribution curve can be subjected to equivalent probability analysis by the contour analysis method in the prior art, and the analysis result is used as the spatial moisture content of the closed drying space, wherein the principle of equivalent probability analysis is based on the assumption that the moisture content in the moisture distribution curve satisfies the normal distribution, and then the probability value of the spatial moisture content is analyzed by the probability distribution function in statistics, and the moisture content corresponding to the maximum probability value is used as the spatial moisture content of the closed drying space.
[0091] It should be noted that the spatial moisture content in the present application reflects the average distribution of moisture content in the closed drying space. The coupling correction in the present application can eliminate the measurement errors caused by equipment errors, environmental changes and other factors. The mapping transformation converts humidity into analyzable moisture content data. Spatial interpolation can provide the moisture content distribution of the entire drying space, not just limited to monitoring point data. This global view can help identify hot spots of moisture content changes, thereby optimizing the control and management of the drying process.
[0092] In step 104, near-infrared spectral information of the target laboratory sample surface is obtained, and the water content of the target laboratory sample surface is trend extrapolated from the water molecule characterization spectrum in the near-infrared spectral information to obtain an extrapolation curve of the surface water content, and then the surface water content of the target laboratory sample is determined based on the extrapolation curve.
[0093] It should be noted that in the present application, the water content of the target laboratory sample surface can be reflected by analyzing the spectral characteristics of the near-infrared spectrometer. In specific implementation, the spectral characteristics of water molecules at designated monitoring points on the target laboratory sample surface can be collected by the near-infrared spectrometer, and then the spectral characteristics of the water molecules can be analyzed to obtain the water content of the designated monitoring points. Furthermore, the distribution trend of the water content of all designated monitoring points can be extrapolated to obtain the distribution curve (extrapolation curve) of the water content on the surface of the target laboratory sample. The water content distribution curve is further feature extracted, and the extracted water content is used as the surface water content of the target laboratory sample. The surface water content in the present application can comprehensively reflect the water content of the target laboratory sample surface.
[0094] In specific implementation, obtaining the near-infrared spectral information of the surface of the target laboratory sample can be achieved in the following manner, namely: the wavelength range of the near-infrared spectrometer (NIR Spectrometer) can be set first, usually the wavelength range of the near-infrared region is between 780nm and 2500nm, and its specific range should be adjusted according to the sample characteristics and analysis requirements, and then the near-infrared spectrometer with the set wavelength range is used to detect the water content of the designated monitoring points on the surface of the target laboratory sample, and then the near-infrared spectral information of the designated monitoring points on the surface of the target laboratory sample is obtained from the database of the near-infrared spectrometer, wherein the near-infrared spectral information is used to analyze the water content of the surface of the target laboratory sample; it should be noted that the designated monitoring points in this application refer to a number of monitoring points designated on the surface of the target laboratory sample, and the monitoring points are evenly distributed on the surface of the target laboratory sample. The specific number of monitoring points can be determined according to the surface area of the target laboratory sample, which will not be elaborated here.
[0095] In some embodiments, the water content of the surface of the target laboratory sample is trend extrapolated from the water molecule characterization spectrum in the near-infrared spectrum information to obtain an extrapolation curve of the surface water content, which can be achieved by the following steps:
[0096] Extracting a water molecule characterization spectrum of water content from the near infrared spectrum information;
[0097] Predicting the water content of the surface of the target laboratory sample according to the water molecule characterization spectrum to obtain the surface predicted water content;
[0098] The distribution trend of the predicted surface moisture content is extrapolated based on the pre-trained extrapolation model to obtain an extrapolation curve of the surface moisture content.
[0099] In specific implementation, the water molecule characterization spectrum of water content can be extracted from the near-infrared spectrum information in the following manner, namely: it should be noted that the water molecule characterization spectrum of water content in the present application refers to a characteristic wavelength (absorption peak) that can reflect the high correlation with water content. In the near-infrared spectrum, water molecules have characteristic absorption peaks near 1400nm and 1900nm. Therefore, the characteristic wavelengths (absorption peaks) near 1400nm and 1900nm can be screened out from the near-infrared spectrum information, and then the principal component analysis in the prior art is used to reduce the noise of the screened characteristic wavelengths, and the partial least squares regression in the prior art is used to further extract the characteristic wavelengths related to the water content, and the extracted characteristic wavelengths are used as the water molecule characterization spectrum of water content; the water content of the surface of the target laboratory sample is predicted based on the water molecule characterization spectrum, The surface predicted moisture content can be obtained in the following manner, namely: first, construct a training data set containing known surface moisture content, pair the preprocessed spectral data with the corresponding moisture content value for training the moisture content prediction model; second, select an algorithm model of the moisture content prediction model, and in this application, use the multivariate linear regression algorithm in the prior art to perform linear regression on the water molecule characterization spectrum (characteristic wavelength); then, use the training data set to train the moisture content prediction model, and use an independent validation set to evaluate the model's prediction performance, thereby completing the training of the moisture content prediction model; finally, input the water molecule characterization spectrum into the trained moisture content prediction model, and output the moisture content of the specified monitoring point on the surface of the target laboratory sample through the moisture content prediction model, and use the set of all moisture contents as the surface predicted moisture content.
[0100] In addition, in the specific implementation, the distribution trend of the predicted surface moisture content is extrapolated based on the pre-trained extrapolation model, and the extrapolation curve of the surface moisture content can be obtained in the following manner, namely: the pre-trained extrapolation model in the present application is to infer the distribution trend of the surface moisture content of the target laboratory sample based on the known moisture content of all designated monitoring points, and the predicted moisture content is regarded as space-moisture content sequence data, and then the distribution trend of the predicted moisture content can be inferred through the linear regression model in the prior art, thereby generating an extrapolation curve of the surface moisture content changing with the surface space.
[0101] It should be noted that the extrapolation curve in the present application is a moisture content prediction curve obtained by extrapolating the distribution trend of the moisture content at the designated monitoring points on the surface of the known target laboratory sample. The extrapolation curve can be used to monitor the changes in moisture content on the surface of the laboratory sample in real time, thereby helping the experimenter to dynamically adjust the experimental conditions and improve the experimental efficiency.
[0102] In some embodiments, reference Figure 3As shown, this figure is a schematic diagram of the process of determining the surface moisture content in some embodiments of the present application. In this embodiment, the surface moisture content of the target laboratory sample can be determined according to the extrapolation curve by the following steps:
[0103] In step 1041, the wet basis moisture content of the target laboratory sample is obtained, and the initial moisture content of the target laboratory sample is determined according to the wet basis moisture content;
[0104] In step 1042, the extrapolation curve is calibrated by the initial water content to obtain an extrapolation calibration curve;
[0105] In step 1043, the surface moisture content of the target laboratory sample is determined based on all predicted moisture contents in the extrapolated calibration curve.
[0106] In specific implementation, the wet basis moisture content of the target laboratory sample is obtained, and the initial moisture content of the target laboratory sample is determined according to the wet basis moisture content. This can be achieved in the following manner, namely: first, the wet basis moisture content of the target laboratory sample is measured by a laboratory wet basis moisture content test technology, and the total mass of the target laboratory sample is measured; then, the product of the total mass and the wet basis moisture content is used as the initial moisture content; the extrapolation curve is calibrated by the initial moisture content, and the extrapolation calibration curve can be obtained in the following manner, namely: an initial prediction is obtained from the extrapolation curve The water content of the target laboratory sample is determined by taking the natural exponential of the opposite number of the absolute difference between the initial water content and the initial predicted water content as a calibration factor, and then multiplying the calibration factor by the predicted water content in the extrapolation curve to complete the calibration of the extrapolation curve, and taking the calibrated extrapolation curve as the extrapolation calibration curve; determining the surface water content of the target laboratory sample according to all the predicted water contents in the extrapolation calibration curve can be achieved in the following manner, that is, the average value of all the predicted water contents in the extrapolation calibration curve can be taken as the surface water content of the target laboratory sample.
[0107] It should be noted that the surface moisture content in the present application comprehensively reflects the moisture content of the surface of the laboratory sample. The larger the surface moisture content, the larger the moisture content of the surface of the target laboratory sample, and the smaller the surface moisture content, the smaller the moisture content of the surface of the target laboratory sample.
[0108] In step 105, an entropy weight fusion evaluation is performed on the moisture content of the target laboratory sample based on the spatial moisture content and the surface moisture content to obtain an evaluation value of the moisture content of the target laboratory sample.
[0109] Obtaining a moisture content distribution curve of the closed drying space, and then determining the information entropy weight of the moisture content of the space according to the moisture content distribution curve;
[0110] Obtaining an extrapolation curve of surface moisture content, and then determining an information entropy weight of the surface moisture content according to the extrapolation curve;
[0111] The spatial moisture content and the surface moisture content are weightedly fused by the information entropy weight of the spatial moisture content and the information entropy weight of the surface moisture content, and the result of the weighted fusion is used as the moisture content evaluation value of the target laboratory sample.
[0112] In the specific implementation, first, all moisture contents of the closed drying space are obtained from the moisture content distribution curve, and all moisture contents of the closed drying space are brought into the information entropy calculation formula to obtain the information entropy of the moisture content in the closed drying space, and the information entropy is used as the spatial information entropy; secondly, all moisture contents of the surface of the target laboratory sample are obtained from the extrapolation curve, and all moisture contents of the surface of the target laboratory sample are brought into the information entropy calculation formula to obtain the information entropy of the surface moisture content of the target laboratory sample, and the information entropy of the surface moisture content is used as the surface information entropy; then, the spatial information entropy and the The sum of the surface information entropies is taken as the sum of information entropies, and then the ratio of the spatial information entropy to the sum of information entropies can be used as the information entropy weight of the spatial moisture content, and the ratio of the surface information entropy to the sum of information entropies can be used as the information entropy weight of the surface moisture content; finally, the product of the information entropy weight of the spatial moisture content and the spatial moisture content is taken as the spatial local moisture content, and the product of the information entropy weight of the surface moisture content and the surface moisture content is taken as the surface local moisture content, and then the sum of the spatial local moisture content and the surface local moisture content is taken as the moisture content evaluation value of the target laboratory sample.
[0113] It should be noted that the moisture content evaluation value in this application can comprehensively consider the changing trend of the moisture content on the surface of the laboratory sample and inside the closed drying space, and accurately evaluate the moisture content of the laboratory sample, which can avoid insufficient drying or local over-drying of the laboratory sample, thereby ensuring that the state of the laboratory sample during the drying process is always in the optimal state, thereby improving the reliability and accuracy of the experimental data.
[0114] In specific implementation, the feedback adjustment of the power of the sample drying device for the environmental monitoring laboratory based on the moisture content evaluation value can be achieved by the following steps, namely: based on the comparison result of the target moisture content at the corresponding moment in the preset moisture content-time curve and the moisture content evaluation value, the heating power of the sample drying device can be feedback-adjusted by the dehumidification and temperature control system, that is, when the moisture content evaluation value is greater than the target moisture content at the corresponding moment in the preset moisture content-time curve, the heating power of the sample drying device is reduced by the dehumidification and temperature control system until the moisture content evaluation value reaches the target moisture content; when the moisture content evaluation value is less than the target moisture content at the corresponding moment in the preset moisture content-time curve, the heating power of the sample drying device is increased by the dehumidification and temperature control system until the moisture content evaluation value reaches the target moisture content; when the moisture content evaluation value is equal to the target moisture content at the corresponding moment in the preset moisture content-time curve, the dehumidification and temperature control system does not perform any processing.
[0115] It should also be noted that in the present application scheme, through multi-point coupled confidence evaluation of the moisture content of the sample, the laboratory sample drying device can better control the drying process of the sample, reduce errors in experimental data analysis, improve the accuracy and reliability of the overall experimental process, and meet the requirements of modern environmental monitoring laboratories for high-precision sample processing.
[0116] On the other hand, in some embodiments, the present application provides a sample drying device for an environmental monitoring laboratory, the sample drying device for an environmental monitoring laboratory comprising a moisture content evaluation unit, referring to Figure 4 , which is a schematic diagram of an exemplary software module of a water content evaluation unit according to some embodiments of the present application, the water content evaluation unit 400 includes: a collection module 401, a processing module 402 and an execution module 403, which are described as follows:
[0117] The collection module 401 in this application is mainly used to collect the humidity of the target laboratory sample at multiple monitoring points in the closed drying space to obtain space humidity data;
[0118] Processing module 402, in the present application, the processing module 402 is used to determine the confidence distance between each monitoring point, and to perform dependency association on the humidity difference in the spatial humidity data through each confidence distance to obtain the humidity dependency relationship between all monitoring points;
[0119] The processing module 402 in the present application is also used to extract the humidity characteristics at each monitoring point from the spatial humidity data, determine the mutual interference coefficient of the sensors between the various monitoring points according to all the humidity characteristics and the humidity dependency, and then perform coupling mapping on the moisture content of the closed drying space based on all the mutual interference coefficients and the spatial humidity data to obtain the spatial moisture content;
[0120] The processing module 402 in the present application is also used to obtain near-infrared spectrum information of the surface of the target laboratory sample, and to perform trend extrapolation on the water content of the surface of the target laboratory sample from the water molecule characterization spectrum in the near-infrared spectrum information to obtain an extrapolation curve of the surface water content, and then determine the surface water content of the target laboratory sample according to the extrapolation curve;
[0121] Execution module 403, in the present application, execution module 403 is mainly used to perform entropy weight fusion evaluation on the moisture content of the target laboratory sample based on the spatial moisture content and the surface moisture content, so as to obtain an evaluation value of the moisture content of the target laboratory sample.
[0122] In addition, the present application also provides a computer device, which includes a memory and a processor, wherein the memory stores codes, and the processor is configured to obtain the codes and execute the above-mentioned method for evaluating the moisture content of laboratory samples.
[0123] In some embodiments, reference Figure 5 , which is a schematic diagram of the structure of a computer device according to some embodiments of the present application using a method for evaluating the moisture content of a laboratory sample. The method for evaluating the moisture content of a laboratory sample in the above embodiment can be performed by Figure 5 The computer device 500 shown in the figure is implemented, and the computer device 500 includes at least one processor 501, a communication bus 502, a memory 503 and at least one communication interface 504.
[0124] The processor 501 may be a general-purpose central processing unit (CPU) or an application-specific integrated circuit (ASIC).
[0125] The communication bus 502 may be used to transmit information between the above-mentioned components.
[0126] The memory 503 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a disk or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 503 may exist independently and be connected to the processor 501 via the communication bus 502. The memory 503 may also be integrated with the processor 501.
[0127] The memory 503 is used to store the program code for executing the solution of the present application, and the execution is controlled by the processor 501. The processor 501 is used to execute the program code stored in the memory 503. The program code may include one or more software modules. The water content assessment method of the laboratory sample in the above embodiment can be implemented by the processor 501 and one or more software modules in the program code in the memory 503.
[0128] The communication interface 504 uses any transceiver or other device for communicating with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.
[0129] In a specific implementation, as an embodiment, a computer device may include multiple processors, each of which may be a single-CPU processor or a multi-CPU processor. The processor here may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).
[0130] The above-mentioned computer device can be a general-purpose computer device or a special-purpose computer device. In a specific implementation, the computer device can be a desktop computer, a portable computer, a network server, a personal digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device or an embedded device. The embodiment of the present application does not limit the type of computer device.
[0131] In addition, the present application also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned method for evaluating the moisture content of a laboratory sample is implemented.
[0132] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.
[0133] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.
Claims
1. A method for evaluating the moisture content of laboratory samples, used in an environmental monitoring laboratory using a sample drying device to evaluate the moisture content of laboratory samples, characterized in that: The method includes: Collect the humidity of the target laboratory sample at multiple monitoring points in the closed drying space to obtain space humidity data; Determine the confidence distance between each monitoring point, and perform dependency association on the humidity difference in the spatial humidity data through each confidence distance to obtain the humidity dependency relationship between all monitoring points; Extracting humidity characteristics at each monitoring point from the spatial humidity data, determining the mutual interference coefficients of sensors between the monitoring points according to all humidity characteristics and the humidity dependency, and then coupling mapping the moisture content of the closed drying space based on all mutual interference coefficients and the spatial humidity data to obtain the spatial moisture content; Acquire near-infrared spectrum information of the surface of the target laboratory sample, perform trend extrapolation on the water content of the surface of the target laboratory sample based on the water molecule characterization spectrum in the near-infrared spectrum information, obtain an extrapolation curve of the surface water content, and then determine the surface water content of the target laboratory sample according to the extrapolation curve; The moisture content of the target laboratory sample is evaluated by entropy weight fusion based on the spatial moisture content and the surface moisture content to obtain an evaluation value of the moisture content of the target laboratory sample.
2. The method according to claim 1, characterized in that Determining the confidence distance between each monitoring point specifically includes: Obtain the humidity data at each monitoring point, and then determine the trend similarity of humidity changes between each monitoring point based on all humidity data; The confidence distance between each monitoring point is determined by the distance between each monitoring point and all trend similarities.
3. The method according to claim 1, characterized in that The humidity differences in the spatial humidity data are correlated by each confidence distance, and the humidity dependency relationship between all monitoring points is obtained, which specifically includes: Extracting humidity differences between various monitoring points from the spatial humidity data; Select two monitoring points as the selected monitoring label pair; Obtain the confidence distance between the monitoring points of the selected monitoring tag pair; Determine the correlation dependency value between the monitoring points in the selected monitoring tag pair through all humidity differences and the confidence distances between the monitoring points in the selected monitoring tag pair; Continue to determine the association dependency values between the monitoring points in the remaining monitoring tag pairs; The dependency matrix composed of all associated dependency values is used as the humidity dependency relationship between all monitoring points.
4. The method according to claim 1, characterized in that Extracting humidity characteristics at each monitoring point from the spatial humidity data specifically includes: Extracting humidity data at each monitoring point from the spatial humidity data; The humidity data at each monitoring point are subjected to characteristic regression fitting to obtain the humidity characteristics at each monitoring point.
5. The method according to claim 1, characterized in that Determining the mutual interference coefficient of sensors between various monitoring points according to all humidity characteristics and the humidity dependency specifically includes: Select two monitoring points as the selected monitoring label pair; Obtaining the associated dependency value between the monitoring points in the selected monitoring tag pair from the humidity dependency relationship; Determine the mutual support of humidity characteristics between monitoring points in the selected monitoring tag pairs; Determine the mutual interference coefficient of sensors between monitoring points in the selected monitoring tag pair through the mutual support and the associated dependency value; Continue to determine the mutual interference coefficients of sensors between monitoring points in the remaining monitoring tag pairs.
6. The method according to claim 1, characterized in that Based on all the mutual interference coefficients and the spatial humidity data, the moisture content of the closed drying space is coupled and mapped, and the spatial moisture content is obtained, which specifically includes: The spatial humidity data is coupled and corrected by all the mutual interference coefficients to obtain corrected humidity data; Mapping the corrected humidity data into the moisture content of each monitoring point; A spatial interpolation operation is performed on the moisture content of each monitoring point to obtain a moisture content distribution curve of the closed drying space, and then the spatial moisture content of the closed drying space is extracted from the moisture content distribution curve.
7. The method according to claim 1, characterized in that The sensor is a humidity sensor.
8. A sample drying device for an environmental monitoring laboratory, the sample drying device for an environmental monitoring laboratory comprising a moisture content evaluation unit, characterized in that: The moisture content assessment unit comprises: A collection module is used to collect the humidity of the target laboratory sample at multiple monitoring points in the closed drying space to obtain space humidity data; A processing module, used to determine the confidence distance between each monitoring point, and to perform dependency association on the humidity difference in the spatial humidity data through each confidence distance to obtain the humidity dependency relationship between all monitoring points; The processing module is further used to extract humidity characteristics at each monitoring point from the spatial humidity data, determine the mutual interference coefficients of sensors between the monitoring points according to all humidity characteristics and the humidity dependency, and then perform coupling mapping on the moisture content of the closed drying space based on all mutual interference coefficients and the spatial humidity data to obtain the spatial moisture content; The processing module is further used to obtain near-infrared spectrum information of the surface of the target laboratory sample, perform trend extrapolation on the water content of the surface of the target laboratory sample from the water molecule characterization spectrum in the near-infrared spectrum information, obtain an extrapolation curve of the surface water content, and then determine the surface water content of the target laboratory sample according to the extrapolation curve; An execution module is used to perform entropy weight fusion evaluation on the moisture content of the target laboratory sample based on the spatial moisture content and the surface moisture content to obtain an evaluation value of the moisture content of the target laboratory sample.
9. A computer device, comprising a memory and a processor, wherein the memory stores a code, characterized in that: The processor is configured to obtain the code and execute the method for evaluating the water content of a laboratory sample according to any one of claims 1 to 7.
10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method for evaluating the water content of a laboratory sample according to any one of claims 1 to 7 is implemented.