Laboratory environment monitoring system and method based on machine vision

Abstract

The invention discloses a laboratory environment monitoring system and method based on machine vision, and the system comprises a vision sensing module which is used for collecting environment index image information of a target laboratory in a historical period; the image analysis module is used for analyzing the index characterization value of the environment index image; the evaluation module is used for determining whether the detection working environment of the target laboratory meets the standard or not; the decision module is used for responding to the target laboratory to detect that the working environment meets the standard and determining whether the target detection instrument meets the risk stability standard or not; and the regulation and control module is used for responding to the condition that the target detection instrument does not conform to the risk stability standard, determining a regulation and control strategy based on a difference value between the risk index characterization value and a preset risk index characterization threshold value, and determining the adjustment amplitude of the image index characterization threshold value. The device has the advantages that the environmental parameters of the laboratory are obtained through machine vision, the laboratory environment independent of a large number of electronic sensors is achieved, and the accuracy and reliability of the detection result are guaranteed.

Description

Technical Field

[0001] This application relates to the field of laboratory result detection technology, and in particular to a laboratory environment monitoring system and method based on machine vision. Background Technology

[0002] In laboratory operations, the accuracy and reliability of laboratory testing fundamentally depend on a strictly controlled physical environment. For example, in high-performance liquid chromatography (HPLC) analysis, key environmental parameters directly affect the instrument's analytical results, operational stability, and lifespan. Specifically, temperature fluctuations can cause chromatographic retention time drift, changes in resolution, and affect detector baseline stability; excessive humidity can corrode circuitry, damage precision components, and even accelerate column performance degradation; excessive light, especially ultraviolet light, can easily cause degradation of photosensitive samples and interfere with the signal-to-noise ratio of fluorescence detectors; and suspended particulate matter in the environment can wear down critical components such as infusion pumps and injection valves, and clog columns and flow cells, leading to abnormal pressure and decreased column efficiency. Therefore, to ensure the accuracy and reproducibility of test data and extend instrument lifespan, the environment must be maintained in a stable, clean, and controlled state during the experiment.

[0003] However, existing laboratory environment monitoring methods lack the ability to analyze visual data, resulting in insufficient perception of key parameters such as temperature, humidity, light intensity, and particulate matter. This leads to problems such as unstable operation of detection instruments, decreased accuracy of measurement results, and reduced overall operational efficiency. Summary of the Invention

[0004] This application provides a laboratory environment monitoring system and method based on machine vision. Its advantage is that it acquires the environmental parameters of the laboratory through machine vision, thereby achieving a laboratory environment that does not rely on a large number of electronic sensors, and ensuring the accuracy and reliability of the test results.

[0005] The technical solution of this application is as follows: On the one hand, this application provides a laboratory environment monitoring system based on machine vision, comprising: The visual sensing module is used to collect environmental indicator image information of the target laboratory over a historical period. The image analysis module, which is connected to the visual sensing module, is used to analyze the image index representation values ​​of environmental indicators. The evaluation module, which is connected to the image analysis module, is used to determine whether the target laboratory testing environment meets the standards. The decision module, which is connected to the evaluation module, is used to respond to whether the target laboratory testing environment meets the standards and to determine whether the target testing instrument meets the risk stability standards. The control module, which is connected to the decision module, is used to respond to situations where the target detection instrument does not meet the risk stability standard. Based on the difference between the risk indicator characterization value and the predetermined risk indicator characterization threshold, the control strategy is determined, and the adjustment range of the image indicator characterization threshold is determined.

[0006] Furthermore, the environmental indicator image information includes temperature image information, humidity image information, light intensity value image information, and particle size image information.

[0007] Furthermore, in the evaluation module, the step of determining whether the target laboratory testing environment meets the standards is as follows: If the image index characterization value is less than the predetermined image index characterization threshold, then the target laboratory testing environment is determined to meet the standard. If the image index characterization value is greater than or equal to the predetermined image index characterization threshold, then the target laboratory testing environment is determined to be non-compliant with the standard.

[0008] Furthermore, in the decision-making module, the step of determining whether the target detection instrument meets the risk stability standard is as follows: Collect risk index parameters of the target detection instrument in the target laboratory within a historical period; analyze the risk index characterization value based on the risk index parameters; If the difference between the risk indicator characterization value and the predetermined risk indicator characterization threshold is less than the predetermined difference threshold, then the target detection instrument is determined to meet the risk stability standard. If the difference between the risk indicator characterization value and the predetermined risk indicator characterization threshold is greater than or equal to the predetermined difference threshold, then the target detection instrument is determined to be non-compliant with the risk stability standard.

[0009] Furthermore, the risk indicator parameters include alarm frequency and data error value.

[0010] On another front, this application provides a machine vision-based laboratory environment monitoring method, comprising the following steps: Collect environmental indicator image information of the target laboratory within a historical period. The environmental indicator image information includes temperature image information, humidity image information, light intensity value image information, and particle size image information. Analyze the characterization values ​​of the environmental indicator images based on the environmental indicator image information; Based on the image index characterization values, determine whether the target laboratory testing environment meets the standards; The response indicates that the target laboratory testing environment meets the standards, and it is determined whether the target testing instruments meet the risk stability standards. If the target detection instrument does not meet the risk stability standard, the adjustment range of the image index characterization threshold is determined based on the difference between the risk index characterization value and the predetermined risk index characterization threshold.

[0011] Furthermore, the image index representation value is determined based on the sum of the first feature-limited representation parameter, the second feature-limited representation parameter, the third feature-limited representation parameter, and the fourth feature-limited representation parameter; The first feature defines the characterization parameter as the ratio of temperature to a predetermined temperature threshold. The second feature defines the characterization parameter as the ratio of humidity to a predetermined humidity threshold. The third feature defines the characterization parameter as the ratio of the light intensity value to a predetermined light intensity threshold. The fourth feature defines the characterization parameter as the ratio of granularity to a predetermined granularity threshold.

[0012] Furthermore, the steps to determine whether the target laboratory testing environment meets the standards are as follows: If the image index characterization value is less than the predetermined image index characterization threshold, then the target laboratory testing environment is determined to meet the standard. If the image index characterization value is greater than or equal to the predetermined image index characterization threshold, then the target laboratory testing environment is determined to be non-compliant with the standard. Furthermore, the steps to determine whether the target detection instrument meets the risk stability standard are as follows: Risk index parameters of the target detection instrument in the target laboratory are collected over a historical period. These risk index parameters include alarm frequency and data error value. The risk index characterization value is then analyzed based on these risk index parameters. The risk indicator value is determined based on the sum of the first risk-limiting parameter and the second risk-limiting parameter; The first risk limitation characteristic parameter is the ratio of the alarm frequency to a predetermined alarm frequency threshold; The second risk limitation characterization parameter is the ratio of the data error value to a predetermined data error threshold; If the difference between the risk indicator characterization value and the predetermined risk indicator characterization threshold is less than the predetermined difference threshold, then the target detection instrument is determined to meet the risk stability standard. If the difference between the risk indicator characterization value and the predetermined risk indicator characterization threshold is greater than or equal to the predetermined difference threshold, then the target detection instrument is determined to be non-compliant with the risk stability standard.

[0013] In summary, the beneficial effects of this application are as follows: 1. The system utilizes a visual sensing module and an image analysis module to achieve a comprehensive quantitative assessment of key environmental parameters such as temperature, humidity, light intensity, and particle size, overcoming the limitations of traditional single-parameter monitoring. By establishing a comprehensive evaluation system encompassing four characteristic parameters, it ensures that the environmental conditions fully comply with testing standards. The decision-making module introduces a dual verification mechanism for instrument operating status, independently assessing the instrument's risk stability based on alarm frequency and data error values. This ensures the accuracy and reliability of the test results from both environmental conditions and instrument status perspectives.

[0014] 2. The system constructs a closed-loop optimization mechanism from environmental monitoring during laboratory testing to threshold adjustment. When deviations occur in instrument operation, the control module can automatically adjust the image indicator threshold based on the difference between the risk indicator value and the threshold, achieving dynamic optimization of monitoring standards. This adaptive adjustment mechanism effectively avoids over- or under-regulation caused by improper environmental standard settings, reducing unnecessary interventions and ensuring timely environmental control, thereby significantly improving the overall efficiency of laboratory testing and the level of system intelligence.

[0015] 3. Detecting environmental parameters using electronic sensors is a common method. However, electronic sensors suffer from complex deployment, synchronization difficulties, and limited environmental adaptability in practical applications. Machine vision analysis methods can fully leverage the non-contact and simultaneous acquisition of multi-dimensional environmental information, effectively overcoming the challenges of deployment and data collaboration in multi-sensor systems. By intelligently associating environmental images with equipment operational risk indicators, a closed-loop control mechanism from environmental monitoring to dynamic adaptive threshold adjustment is established. This not only significantly reduces reliance on dedicated hardware and the overall cost throughout the system's lifecycle but also improves the accuracy of environmental state perception and the intelligence of system regulation through data-driven decision-making processes, thereby ensuring the reliability and stability of detection results at a higher level. Attached Figure Description

[0016] Figure 1 This is an architecture diagram of a laboratory environment monitoring system based on machine vision, according to an embodiment of the present invention. Figure 2 This is a flowchart illustrating the steps of a laboratory environment monitoring method based on machine vision, according to an embodiment of the present invention. Figure 3 A logic diagram for determining whether the target laboratory testing environment meets the standards provided in this embodiment of the invention; Figure 4 This is a logic diagram for determining whether a target detection instrument meets the risk stability standard, provided in an embodiment of the present invention. Detailed Implementation

[0017] The specific embodiments of this application are described in detail below with reference to the accompanying drawings.

[0018] Example 1: A laboratory environment monitoring system based on machine vision, comprising: The visual sensing module is used to collect environmental indicator image information of the target laboratory over a historical period. The image analysis module, which is connected to the visual sensing module, is used to analyze the image representation values ​​of environmental indicators. The evaluation module, which is connected to the image analysis module, is used to determine whether the target laboratory testing environment meets the standards. If the image index characterization value is less than the predetermined image index characterization threshold, then the target laboratory testing environment is determined to meet the standard. If the image index characterization value is greater than or equal to the predetermined image index characterization threshold, then the target laboratory testing environment is determined to be non-compliant with the standard. The decision module, which is connected to the evaluation module, is used to determine whether the target laboratory's testing instruments meet the risk stability standards in response to the target laboratory's testing environment meeting the standards. Collect risk indicator parameters of the target laboratory's testing instruments over a historical period; analyze the risk indicator characterization values ​​based on the risk indicator parameters. If the difference between the risk indicator characterization value and the predetermined risk indicator characterization threshold is less than the predetermined difference threshold, then the target laboratory testing instrument is determined to meet the risk stability standard. If the difference between the risk indicator characterization value and the predetermined risk indicator characterization threshold is greater than or equal to the predetermined difference threshold, then the target laboratory testing instrument is determined to be non-compliant with the risk stability standard. The control module, which is connected to the decision module, is used to respond to situations where the target detection instrument does not meet the risk stability standard. Based on the difference between the risk indicator characterization value and the predetermined risk indicator characterization threshold, the control strategy is determined, and the adjustment range of the image indicator characterization threshold is determined.

[0019] The environmental indicator image information includes temperature image information, humidity image information, light intensity value image information, and particle size image information; The risk indicator parameters include alarm frequency and data error value.

[0020] In this embodiment, a closed-loop system consisting of visual sensing, image analysis, evaluation, decision-making, and control modules is constructed to achieve automated, data-driven integrated management of the laboratory environment and testing instruments. The system first uses the visual sensing and image analysis modules to comprehensively and continuously collect and quantify environmental indicators such as temperature, humidity, light intensity, and particulate matter. The evaluation module automatically determines environmental compliance. Based on compliance, the decision-making module further analyzes risk parameters such as instrument alarm frequency and data errors to assess operational stability. Finally, when instrument stability fails to meet standards, the control module dynamically adjusts environmental threshold standards in reverse, forming an adaptive optimization cycle centered on ensuring instrument accuracy and reliability. This not only significantly improves the efficiency of laboratory monitoring and preventative maintenance capabilities but also, through intelligent linkage between environmental and equipment status, fundamentally ensures the accuracy of testing data, operational safety, and continuous optimization of the overall laboratory operational quality.

[0021] The condition for the visual sensing module to convert the environmental indicator image information of the target laboratory within a historical period into quantifiable image features is as follows: Collect temperature, humidity, light intensity, and particle size images of the target laboratory over a historical period. The visual transmission module captures images from a liquid column thermometer to determine the temperature value. The visual transmission module captures images from the hygrometer to determine humidity values. Extract the light intensity signal received by the imaging element and analyze the overall brightness of the image to determine the light intensity; The number, brightness, and size of scattered light points in statistical images are extracted to determine particulate matter in the air.

[0022] In this embodiment, the visual sensing module converts various environmental parameters into quantifiable image features, captures images of liquid column thermometers using visual sensing, and identifies temperature values ​​from the images; identifies humidity values ​​by capturing images of hygrometers; directly calculates light intensity by analyzing the overall brightness of the image based on the light intensity signal received by the imaging element; and accurately analyzes the concentration and distribution of particulate matter in the air by statistically analyzing the number, brightness, and size of scattered light points in the image based on the principle of laser scattering.

[0023] In this embodiment, a visual sensing module enables non-contact, integrated, synchronous acquisition and precise analysis of multi-dimensional environmental parameters such as temperature, humidity, light, and particulate matter in the laboratory. Machine vision technology directly reads data from images of traditional instruments like liquid column thermometers and hygrometers, eliminating the need for numerous electronic sensors and significantly reducing system cost and wiring complexity. Simultaneously, intelligent analysis of overall image brightness and scattered light points transforms physical quantities that are difficult to image directly into quantifiable image features. This not only achieves the fusion acquisition of multi-source environmental information, ensuring data consistency in time and space, but also overcomes the limitations of traditional sensors deployed in specific environments, providing a unified, reliable, and high-precision data foundation for subsequent environmental assessments and system decisions.

[0024] The image analysis module analyzes the image index representation value, which is determined based on the sum of the first feature-limited representation parameter, the second feature-limited representation parameter, the third feature-limited representation parameter, and the fourth feature-limited representation parameter. The first feature defines the characterization parameter as the ratio of temperature to a predetermined temperature threshold. The second feature defines the characterization parameter as the ratio of humidity to a predetermined humidity threshold. The third feature defines the characterization parameter as the ratio of the light intensity value to a predetermined light intensity threshold. The fourth feature defines the characterization parameter as the ratio of granularity to a predetermined granularity threshold.

[0025] In this embodiment, the predetermined temperature threshold, humidity threshold, light intensity threshold, and particle size threshold are all obtained in advance. The temperature, humidity, light intensity, and particle size of the target laboratory are collected within 3 months of stable operation of the testing operation, and their average values ​​are calculated as the predetermined temperature threshold, humidity threshold, light intensity threshold, and particle size threshold.

[0026] In this embodiment, the system comprehensively acquires environmental images through the visual sensing module, while the image analysis module accurately calculates the environmental indicator values ​​through a comprehensive quantitative model, making the environmental assessment more scientific and objective and fundamentally improving the reliability of the detection data.

[0027] The evaluation module determines that the target laboratory testing environment meets the standard if the image index characterization value is less than the predetermined image index characterization threshold.

[0028] In this embodiment, the predetermined image index characterization threshold is obtained in advance. The image index characterization values ​​are extracted within 3 months of stable operation of the target laboratory detection operation, and the average value is calculated as the predetermined image index characterization threshold. The predetermined image index characterization threshold is selected in the range of [3.95, 4.35], and the preferred value in this embodiment is 4.10.

[0029] The evaluation module determines that the condition for the target laboratory testing environment to be non-compliant with the standard is that the image index characterization value is greater than or equal to the predetermined image index characterization threshold.

[0030] In this embodiment, the predetermined image index characterization threshold is obtained in advance. The image index characterization values ​​are extracted within 3 months of stable operation of the target laboratory detection operation, and the average value is calculated as the predetermined image index characterization threshold. The predetermined image index characterization threshold is selected in the range of [3.95, 4.35], and the preferred value in this embodiment is 4.10.

[0031] In this embodiment, by setting clear image index characterization thresholds, the compliance of laboratory testing environments is automated, objective, and rapidly determined, replacing the vague assessment that relies on subjective human judgment. This makes the environmental monitoring results standardized and the conclusions clear, enabling immediate triggering of early warnings or initiation of subsequent processes. Consequently, the efficiency and reliability of environmental monitoring are significantly improved, providing timely and accurate decision-making basis for the standardized management and risk prevention of laboratories.

[0032] The response to the target laboratory testing environment meeting the standards is that the risk indicator characterization value is determined based on the sum of the first risk-limiting characterization parameter and the second risk-limiting characterization parameter: The first risk limitation characteristic parameter is the ratio of the alarm frequency to a predetermined alarm frequency threshold; The second risk limitation characterization parameter is the ratio of the data error value to a predetermined data error threshold.

[0033] In this embodiment, the formula for calculating the alarm frequency is: Alarm frequency = Total number of alarms / Total time The formula for calculating the data error value is: Error = Measured value - True value In this embodiment, the predetermined alarm frequency threshold and data error threshold are obtained in advance. The alarm frequency and data error values ​​of the target instrument during the target laboratory testing operation within 3 months of stable operation are extracted, and their average values ​​are calculated as the predetermined alarm frequency threshold and data error threshold.

[0034] In this embodiment, a quantitative evaluation model based on alarm frequency and data error value is constructed to achieve a precise and objective comprehensive assessment of the risk stability of laboratory testing instruments. The final risk index characterization value is determined by adding the ratios of the two key risk parameters—alarm frequency and data error value—to their respective thresholds, unifying multi-dimensional and heterogeneous risk factors into a single quantifiable comprehensive indicator. This integrated evaluation method avoids the limitations of a single indicator, providing a more comprehensive and realistic reflection of the overall operating status and reliability of the instrument. It offers a scientific and clear basis for decision-making, further ensuring the accuracy of testing data and the stability of instrument operation under the premise of environmental compliance, ultimately providing dual protection for the quality and reliability of laboratory testing results.

[0035] The decision module responds to the fact that the target laboratory testing environment meets the standard and determines that the target testing instrument meets the risk stability standard when the difference between the risk indicator characterization value and the predetermined risk indicator characterization threshold is less than the predetermined difference threshold.

[0036] In this embodiment, the predetermined risk indicator characterization threshold and the difference threshold are both obtained in advance. The predetermined image indicator characterization threshold is selected in the range of [1.95, 2.35], and preferably 2.10 in this embodiment; the predetermined difference threshold is selected in the range of [0.05, 0.35], and preferably 0.15 in this embodiment.

[0037] The decision module determines that the target testing instrument does not meet the risk stability standard in response to the target laboratory testing environment meeting the standard. The condition is that the difference between the risk indicator characterization value and the predetermined risk indicator characterization threshold is greater than or equal to the predetermined difference threshold.

[0038] In this embodiment, the predetermined risk indicator characterization threshold and the difference threshold are both obtained in advance. The predetermined image indicator characterization threshold is selected in the range of [1.95, 2.35], and preferably 2.10 in this embodiment; the predetermined difference threshold is selected in the range of [0.05, 0.35], and preferably 0.15 in this embodiment.

[0039] In this embodiment, by introducing a difference threshold as the core criterion for determining instrument stability, it not only provides a conclusion on whether the instrument meets or does not meet the standard, but also quantifies the severity of the instrument's deviation from the standard by comparing the difference with a preset threshold. This avoids repeated fluctuations in the state near the critical value, enhancing the stability and fault tolerance of the system's decision-making. More importantly, it provides precise and quantifiable input for subsequent control modules, enabling any corrective measures for instrument instability to be precisely triggered and adjusted as needed based on the severity of the deviation. This achieves a leap from simple monitoring to preventative, refined, and intelligent operation and maintenance.

[0040] In response to the target detection instrument failing to meet the risk stability standard, the control module determines the adjustment range of the image index characterization threshold based on the difference between the risk index characterization value and the predetermined risk index characterization threshold.

[0041] In this embodiment, the predetermined risk index characterization threshold is obtained in advance, and the predetermined image index characterization threshold is selected within the range of [1.95, 2.35], with 2.10 being the preferred value in this embodiment.

[0042] In this embodiment, by dynamically linking the instrument's risk status with environmental standards, an intelligent closed-loop control system with self-optimization capabilities is realized. When a testing instrument is determined to be non-compliant with the standard, the system does not simply issue an alarm. Instead, it precisely and proportionally adjusts the image index representation threshold according to the severity of the risk deviation. This allows the system to intelligently and adaptively tighten environmental standards. By creating a more demanding and less fault-tolerant operating environment for critical instruments, the system proactively compensates for their performance degradation, thereby fundamentally intervening in the risk, protecting unstable instruments, and maintaining the reliability of the overall testing results. This achieves a leap from passive monitoring to proactive protection.

[0043] The condition under which the control module does not perform control is that the target laboratory testing environment meets the standards and the target testing instrument does not meet the risk stability standards.

[0044] In this embodiment, by precisely defining the activation conditions of the control module, the system intervention is made more precise and the separation of responsibilities is clearer. This effectively prevents the system from making ineffective or even harmful adjustments, thereby avoiding energy waste and operational redundancy, and eliminating the risk of affecting other normal instruments due to erroneous intervention. It directly guides maintenance personnel's attention to the calibration, maintenance, or replacement of the instruments themselves, ensuring the accuracy of fault diagnosis and the efficiency of maintenance actions, fundamentally improving the intelligence level and operational efficiency of the entire system.

[0045] In this embodiment, a closed-loop optimization mechanism is constructed, encompassing environmental monitoring during laboratory testing and threshold adjustment. When deviations occur in the instrument's operating status, the control module automatically adjusts the image indicator threshold based on the difference between the risk indicator value and the threshold, achieving dynamic optimization of the monitoring standard. This adaptive adjustment mechanism effectively avoids over- or under-regulation caused by improper environmental standard settings, reducing unnecessary interventions and ensuring timely environmental control. Consequently, it significantly improves the overall efficiency of laboratory testing and the system's intelligent operation level.

[0046] Example 2: A laboratory environment monitoring method based on machine vision, comprising the following steps: Collect environmental indicator image information of the target laboratory within a historical period. The environmental indicator image information includes temperature image information, humidity image information, light intensity value image information, and particle size image information. Analyze the characterization values ​​of the environmental indicator images based on the environmental indicator image information; Based on the image index characterization values, determine whether the target laboratory testing environment meets the standards; The response indicates that the target laboratory testing environment meets the standards, and it is determined whether the target testing instruments meet the risk stability standards. If the target detection instrument does not meet the risk stability standard, the adjustment range of the image index characterization threshold is determined based on the difference between the risk index characterization value and the predetermined risk index characterization threshold.

[0047] Furthermore, the image index representation value is determined based on the sum of the first feature-limited representation parameter, the second feature-limited representation parameter, the third feature-limited representation parameter, and the fourth feature-limited representation parameter; The first feature defines the characterization parameter as the ratio of temperature to a predetermined temperature threshold. The second feature defines the characterization parameter as the ratio of humidity to a predetermined humidity threshold. The third feature defines the characterization parameter as the ratio of the light intensity value to a predetermined light intensity threshold. The fourth feature defines the characterization parameter as the ratio of granularity to a predetermined granularity threshold.

[0048] Furthermore, the steps to determine whether the target laboratory testing environment meets the standards are as follows: If the image index characterization value is less than the predetermined image index characterization threshold, then the target laboratory testing environment is determined to meet the standard. If the image index characterization value is greater than or equal to the predetermined image index characterization threshold, then the target laboratory testing environment is determined to be non-compliant with the standard. Furthermore, the steps to determine whether the target detection instrument meets the risk stability standard are as follows: Risk index parameters of the target detection instrument in the target laboratory are collected over a historical period. These risk index parameters include alarm frequency and data error value. The risk index characterization value is then analyzed based on these risk index parameters. The risk indicator value is determined based on the sum of the first risk-limiting parameter and the second risk-limiting parameter; The first risk limitation characteristic parameter is the ratio of the alarm frequency to a predetermined alarm frequency threshold; The second risk limitation characterization parameter is the ratio of the data error value to a predetermined data error threshold; If the difference between the risk indicator characterization value and the predetermined risk indicator characterization threshold is less than the predetermined difference threshold, then the target detection instrument is determined to meet the risk stability standard. If the difference between the risk indicator characterization value and the predetermined risk indicator characterization threshold is greater than or equal to the predetermined difference threshold, then the target detection instrument is determined to be non-compliant with the risk stability standard.

[0049] In this embodiment, machine vision industrial cameras are deployed to achieve comprehensive environmental monitoring of key process areas in a non-contact manner, thereby ensuring the stability of the macro-manufacturing environment. In practical applications, even if environmental parameters consistently meet standards, abnormal fluctuations in product qualification rates may still occur. Visual quality inspection data from the production process can be introduced. While continuously monitoring environmental parameters, the system can integrate high-resolution vision units to perform real-time visual inspection of target samples in key product processes, extracting process quality index parameters. These process quality indicators are then input into the decision-making module as new risk parameters. When the system detects that the environmental conditions are compliant but the product qualification rate declines, it can identify the root cause as equipment performance degradation. The control module will no longer be limited to adjusting environmental thresholds; it can automatically trigger the equipment calibration process, dynamically adjusting the equipment operating parameters with precision. By integrating machine vision and environmental monitoring, a closed-loop intelligent quality control system is constructed, solving the problem of abnormal fluctuations in product qualification rates caused by hidden factors such as equipment performance degradation when laboratory environmental parameters meet standards.

[0050] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several modifications and improvements can be made without departing from the inventive concept of this application, and these all fall within the protection scope of this application.

Claims

1. A laboratory environment monitoring system based on machine vision, characterized in that, include: The visual sensing module is used to collect environmental indicator image information of the target laboratory over a historical period. The image analysis module, which is connected to the visual sensing module, is used to analyze the image index representation values ​​of environmental indicators. The evaluation module, which is connected to the image analysis module, is used to determine whether the target laboratory testing environment meets the standards. The decision module, which is connected to the evaluation module, is used to respond to whether the target laboratory testing environment meets the standards and to determine whether the target testing instrument meets the risk stability standards. The control module, which is connected to the decision module, is used to respond to situations where the target detection instrument does not meet the risk stability standard. Based on the difference between the risk indicator characterization value and the predetermined risk indicator characterization threshold, the control strategy is determined, and the adjustment range of the image indicator characterization threshold is determined.

2. The laboratory environment monitoring system based on machine vision according to claim 1, characterized in that, The environmental indicator image information includes temperature image information, humidity image information, light intensity value image information, and particle size image information.

3. The laboratory environment monitoring system based on machine vision according to claim 1, characterized in that, In the evaluation module, the steps for determining whether the target laboratory testing environment meets the standards are as follows: If the image index characterization value is less than the predetermined image index characterization threshold, then the target laboratory testing environment is determined to meet the standard. If the image index characterization value is greater than or equal to the predetermined image index characterization threshold, then the target laboratory testing environment is determined to be non-compliant with the standard.

4. The laboratory environment monitoring system based on machine vision according to claim 1, characterized in that, In the decision-making module, the step of determining whether the target detection instrument meets the risk stability standard is as follows: Collect risk index parameters of the target detection instrument in the target laboratory within a historical period; analyze the risk index characterization value based on the risk index parameters; If the difference between the risk indicator characterization value and the predetermined risk indicator characterization threshold is less than the predetermined difference threshold, then the target detection instrument is determined to meet the risk stability standard. If the difference between the risk indicator characterization value and the predetermined risk indicator characterization threshold is greater than or equal to the predetermined difference threshold, then the target detection instrument is determined to be non-compliant with the risk stability standard.

5. The laboratory environment monitoring system based on machine vision according to claim 4, characterized in that, The risk indicator parameters include alarm frequency and data error value.

6. A laboratory environment monitoring method based on machine vision, characterized in that, Includes the following steps: Collect environmental indicator image information of the target laboratory within a historical period. The environmental indicator image information includes temperature image information, humidity image information, light intensity value image information, and particle size image information. Analyze the characterization values ​​of the environmental indicator images based on the environmental indicator image information; Based on the image index characterization values, determine whether the target laboratory testing environment meets the standards; The response indicates that the target laboratory testing environment meets the standards, and it is determined whether the target testing instruments meet the risk stability standards. If the target detection instrument does not meet the risk stability standard, the adjustment range of the image index characterization threshold is determined based on the difference between the risk index characterization value and the predetermined risk index characterization threshold.

7. The laboratory environment monitoring method based on machine vision according to claim 6, characterized in that, The image index representation value is determined based on the sum of the first feature-limited representation parameter, the second feature-limited representation parameter, the third feature-limited representation parameter, and the fourth feature-limited representation parameter; The first feature defines the characterization parameter as the ratio of temperature to a predetermined temperature threshold. The second feature defines the characterization parameter as the ratio of humidity to a predetermined humidity threshold. The third feature defines the characterization parameter as the ratio of the light intensity value to a predetermined light intensity threshold. The fourth feature defines the characterization parameter as the ratio of granularity to a predetermined granularity threshold.

8. The laboratory environment monitoring method based on machine vision according to claim 7, characterized in that, The steps to determine whether the target laboratory testing environment meets the standards are as follows: If the image index characterization value is less than the predetermined image index characterization threshold, then the target laboratory testing environment is determined to meet the standard. If the image index characterization value is greater than or equal to the predetermined image index characterization threshold, then the target laboratory testing environment is determined to be non-compliant with the standard.

9. The laboratory environment monitoring method based on machine vision according to claim 6, characterized in that, The steps to determine whether a target detection instrument meets the risk stability standard are as follows: Collect risk index parameters of the target detection instruments in the target laboratory over a historical period. The risk index parameters include alarm frequency and data error value. Analyze the risk indicator characterization values ​​based on the aforementioned risk indicator parameters; The risk indicator value is determined based on the sum of the first risk-limiting parameter and the second risk-limiting parameter; The first risk limitation characteristic parameter is the ratio of the alarm frequency to a predetermined alarm frequency threshold; The second risk limitation characterization parameter is the ratio of the data error value to a predetermined data error threshold; If the difference between the risk indicator characterization value and the predetermined risk indicator characterization threshold is less than the predetermined difference threshold, then the target detection instrument is determined to meet the risk stability standard. If the difference between the risk indicator characterization value and the predetermined risk indicator characterization threshold is greater than or equal to the predetermined difference threshold, then the target detection instrument is determined to be non-compliant with the risk stability standard.

Images