Laboratory equipment operation monitoring system

Abstract

The invention relates to the technical field of equipment monitoring, in particular to a laboratory equipment operation monitoring system which comprises a server side and a user side. The server comprises an arrangement module, an association module, a data acquisition module, a risk judgment module, a risk identification module and an association module; wherein the risk identification module is used for acquiring sensor data of other sensors and operation data of other devices in a preset range according to identified sensor data with risks and operation data corresponding to abnormal devices; inputting the data of the sensor with the risk, the operation data corresponding to the equipment with the abnormity, the data of the sensor of other sensors in a preset range and the operation data of other equipment into a preset risk identification model as input data, and outputting corresponding risk abnormity reason data; and the association module is used for associating the output risk abnormity reason data with the corresponding sensor or equipment and sending the data to the corresponding user side.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment monitoring, and in particular to a laboratory equipment operation monitoring system. Background Art

[0002] With the development of science and technology, laboratory equipment plays an increasingly important role in scientific research, production and manufacturing, etc. In order to ensure the normal operation of laboratory equipment, it is very important to monitor and manage it effectively.

[0003] At present, laboratory equipment operation monitoring systems mainly rely on various sensors installed on the equipment to collect data and detect the operating status of the equipment through data analysis algorithms. However, although the existing laboratory equipment operation monitoring system has achieved the monitoring of equipment status to a certain extent, it has the following shortcomings when analyzing the causes of abnormalities:

[0004] Existing systems usually perform anomaly detection and analysis based on data from a single sensor only, and fail to fully consider the relationships and influences between data from multiple sensors. This isolated analysis method easily ignores the complex relationships within the equipment, resulting in inaccurate analysis of the causes of anomalies, making it difficult to reveal the true source of the fault, and making it impossible to achieve accurate and reliable analysis of the causes of anomalies.

[0005] Based on this, there is an urgent need for a laboratory equipment operation monitoring system that can accurately and reliably analyze the abnormal causes corresponding to equipment abnormalities during the process of monitoring laboratory equipment, greatly improving the reliability and accuracy of abnormality detection. Summary of the invention

[0006] One of the purposes of the present invention is to provide a laboratory equipment operation monitoring system, which can accurately and reliably analyze the abnormal causes corresponding to equipment abnormalities during the process of monitoring laboratory equipment, thereby greatly improving the reliability and accuracy of abnormality detection.

[0007] In order to achieve the above-mentioned purpose, a laboratory equipment operation monitoring system is provided, including a server and a user;

[0008] The server includes:

[0009] A deployment module is used to deploy sensors in various laboratories in the building and on various equipment in the laboratories;

[0010] The data acquisition module is used to acquire the sensor data collected by each sensor; it is also used to collect the operation data corresponding to each device in the laboratory;

[0011] The risk judgment module is used to judge whether each sensor data has risks based on the sensor data collected by each sensor, and identify the sensor data with risks; it is also used to judge whether the operating status of each device in each laboratory is abnormal based on the operating data corresponding to each device in each laboratory, and identify the abnormal device;

[0012] A risk identification module is used to obtain sensor data of other sensors within a preset range and operating data of other devices based on the identified sensor data with risks and operating data corresponding to the equipment with abnormalities, and input the sensor data with risks, operating data corresponding to the equipment with abnormalities, and sensor data of other sensors within the preset range and operating data of other devices as input data into a preset risk identification model, and output corresponding risk abnormality cause data;

[0013] The association module is used to associate the output risk abnormality cause data with the corresponding sensor or device and send it to the corresponding user end.

[0014] The technical principle and effect of this solution: In this solution, first, sensors are arranged in each laboratory in the building and on each device in the laboratory. The sensors are used to monitor the environment of the laboratory and each device, thereby realizing all-round monitoring of the laboratory. After the arrangement is completed, the sensor data corresponding to each sensor and the operating data corresponding to each device in the laboratory are obtained. Then, the sensor data corresponding to each sensor is judged whether there is a risk, and the sensor data corresponding to the sensor with risk is identified. At the same time, the operating data of each device is judged whether the operating status of each device is abnormal, and the abnormal device is identified. At this time, the system has completed the identification and screening of sensors with risk and equipment with abnormal operation.

[0015] Then, based on these risky sensors and abnormally operating devices, the sensor data of other sensors within a preset range and the operating data of other devices are obtained. Afterwards, not only the sensor data corresponding to the identified risky sensors and the operating data of the abnormally operating devices are input into the preset risk identification model as input data, but also the sensor data of other sensors within the preset range and the operating data of other devices are also input as input data. Through the input of these two types of data, the corresponding risk abnormality cause data is output.

[0016] Compared with the existing risk identification, which directly inputs abnormal data into the model for abnormal cause analysis, the present application not only relies on the abnormal data itself, that is, the data corresponding to the risky sensor and the abnormally operating equipment, but also combines other sensor data within the preset range and the operating data of other equipment, thereby providing a more comprehensive data set. This enables the model to analyze the abnormal causes from multiple dimensions, improving the accuracy and reliability of abnormal diagnosis. By considering other sensor data within the preset range, the model can better understand the environment and background of the current abnormal data, rather than looking at the data at a specific point in isolation. This can better understand the causes of abnormal phenomena, such as changes in environmental factors that may cause a certain device to be abnormal. By comprehensively analyzing the risky sensor data, the abnormal equipment data and other related data, the model can more accurately identify abnormal patterns and provide more specific abnormal cause analysis. This method can reduce false positives and false negatives, improve the detection accuracy of the system, and can accurately and reliably analyze the abnormal causes corresponding to the equipment abnormalities in the process of monitoring laboratory equipment, greatly improving the reliability and accuracy of abnormal detection.

[0017] Finally, the output risk abnormality cause data will be associated with the corresponding sensor or equipment and sent to the corresponding user end, thereby achieving accurate and reliable monitoring and early warning of laboratory equipment.

[0018] Furthermore, the server also includes:

[0019] The risk elimination module is used to identify the various risk characteristic factors corresponding to the risk abnormality cause data based on the output risk abnormality cause data, and retrieve the risk resolution strategies associated with each risk characteristic factor from the database to form a risk resolution strategy set corresponding to the output risk abnormality cause data.

[0020] Beneficial effects: In this solution, the output risk abnormality cause data will first be parsed to extract relevant risk characteristic factors. These characteristic factors may be specific parameters or conditions that cause abnormalities, such as excessive temperature, excessive current, increased vibration, etc. Then, based on the identified risk characteristic factors, the corresponding risk solution strategies are retrieved from the preset database. These strategies can be predefined operating procedures, maintenance guidelines, or emergency response measures, which integrate the identified risk characteristic factors with the corresponding solution strategies to form a specific solution for the current risk abnormality cause data. This can be an operation manual, a list of steps, or a series of commands executed by an automated system.

[0021] By automatically identifying risk characteristic factors and generating solution strategies, the need for manual intervention is reduced and processing efficiency is improved.

[0022] All risk resolution strategies are standard operating procedures retrieved from the database, ensuring the consistency and standardization of the processing process and avoiding operational inconsistencies caused by human factors.

[0023] Furthermore, the server also includes:

[0024] The point management module is used to visually manage sensors and devices in each laboratory in the building and on each device in the laboratory.

[0025] Beneficial effects: The layout and status of each laboratory and equipment in the building are displayed through a visual interface, so that managers can understand the operation of the entire system at a glance. The information of all laboratories, equipment and their sensors is centrally managed on the same platform, which improves management efficiency. The data of different equipment and sensors are integrated to provide a unified data view for comprehensive analysis. That is, by introducing the point management module, the management of equipment and sensors in the laboratory becomes more intuitive and efficient. This module not only improves the convenience and response speed of management, but also enhances the flexibility and scalability of the system. In addition, centralized management and data integration can also improve the efficiency of troubleshooting and provide support for preventive maintenance.

[0026] Furthermore, the point management module includes:

[0027] A selection matching module is used to identify the selected device corresponding to the feedback information according to the feedback information corresponding to the user end, and match all sensors and corresponding sensor data under the selected device from the database according to the selected device;

[0028] The data display module is used to generate a corresponding trend analysis chart based on the selected device, all sensors under the selected device and the corresponding sensor data, based on a preset trend screening strategy, and feed it back to the corresponding user end.

[0029] Beneficial effects: The selection matching module can automatically identify the selected device based on the feedback information from the user end, and match all sensors and their data under the device from the database. This improves the accuracy and efficiency of data processing and reduces the possibility of manual input errors. Through the automatic matching function, users do not need to manually search or enter device information, which greatly simplifies the operation process.

[0030] The data display module generates trend analysis charts based on the selected equipment and its sensor data, visually displaying the changing trend of the equipment's operating status. Through the preset trend screening strategy, the system can automatically select the most relevant data for display, helping users to quickly identify abnormal situations. That is, by introducing the selection matching module and the data display module, the point management module achieves accurate matching and trend analysis of the selected equipment and its sensor data. This design not only improves the accuracy and efficiency of data processing, but also enhances the system's real-time feedback capabilities and user-friendliness, providing strong support for the management and maintenance of laboratory equipment.

[0031] Furthermore, the preset trend screening strategy is:

[0032] Determine the screening type corresponding to this screening according to the selected device and all sensors under the selected device and the corresponding sensor data, and screen the sensor data according to the screening type; the screening type includes time screening and point screening;

[0033] If the filter type is time filter, the time period corresponding to this filter is determined, and the sensor data corresponding to each sensor corresponding to the time period is selected;

[0034] If the screening type is point screening, the sensor corresponding to this screening is determined, and the sensor data corresponding to the determined sensor is selected;

[0035] According to the selected sensor data, based on the preset trend screening rule set, the trend screening rule corresponding to this calculation is selected, the trend calculation is performed on the corresponding sensor data through the selected trend screening rule, and the calculation result is converted into a trend analysis chart.

[0036] Beneficial effects: Through the preset trend screening strategy, the point management module realizes the accurate screening and trend analysis of the selected equipment and its sensor data. This strategy not only improves the accuracy and efficiency of data processing, but also enhances the real-time feedback capability and user-friendliness of the system, providing strong support for the management and maintenance of laboratory equipment. Users can flexibly select the screening type according to actual needs, and intuitively understand the operating status and development trend of the equipment through the trend analysis chart, so as to make more reasonable decisions. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 This is a logic block diagram of the laboratory equipment operation monitoring system in Example 1 of the present invention. DETAILED DESCRIPTION

[0038] The following is further described in detail through specific implementation methods:

[0039] Embodiment 1

[0040] Laboratory equipment operation monitoring system, basically Figure 1 As shown, it includes a server and a user;

[0041] The server includes:

[0042] The deployment module is used to deploy sensors in various laboratories in the building and on various devices in the laboratories. In this embodiment, the sensors not only perform real-time detection on the devices themselves, but also monitor the laboratory environment in real time, thereby achieving all-round monitoring of the laboratory.

[0043] The data acquisition module is used to acquire the sensor data collected by each sensor; it is also used to collect the operation data corresponding to each device in the laboratory;

[0044] The risk judgment module is used to judge whether each sensor data has risks based on the sensor data collected by each sensor, and identify the sensor data with risks; it is also used to judge whether the operating status of each device in each laboratory is abnormal based on the operating data corresponding to each device in each laboratory, and identify the abnormal devices; in this solution, the sensor data and the equipment operating data are used to quickly judge the sensor abnormalities and equipment abnormalities.

[0045] The risk identification module is used to obtain sensor data of other sensors within a preset range and operating data of other equipment based on the identified sensor data with risks and operating data corresponding to the equipment with abnormalities, and input the sensor data with risks, operating data corresponding to the equipment with abnormalities, and sensor data of other sensors within the preset range and operating data of other equipment as input data into a preset risk identification model, and output corresponding risk abnormality cause data; in this embodiment, the risk identification model is constructed using a BP neural network model, and of course in other embodiments, the risk identification model can also be constructed using AI.

[0046] In this embodiment, a three-layer BP neural network model is first constructed, including an input layer, a hidden layer and an output layer. In this embodiment, the sensor data with risks, the operation data corresponding to the equipment with abnormalities, and the sensor data of other sensors within a preset range and the operation data of other equipment are used as inputs of the input layer, so the input layer has 4 nodes, and the output is a prediction of the risk abnormality cause data, so there is a total of 1 node; for the hidden layer, this embodiment uses the following formula to determine the number of hidden layer nodes: Wherein, Z is the number of nodes in the hidden layer, n is the number of nodes in the input layer, m is the number of nodes in the output layer, and a is a number between 1 and 10. In this embodiment, it is taken as 5, so there are 7 nodes in the hidden layer. BP neural network usually uses Sigmoid differentiable function and linear function as the excitation function of the network. This paper selects the S-type tangent function tansig as the excitation function of the hidden layer neurons. The prediction model selects the S-type logarithmic function tansig as the excitation function of the output layer neurons.

[0047] The association module is used to associate the outputted risk abnormality cause data with the corresponding sensor or device and send it to the corresponding user end. In this embodiment, it also includes a monitoring module, which is used to set up monitoring devices in each laboratory, perform real-time video monitoring of each laboratory, and send the corresponding monitoring video of the corresponding laboratory to the user end when the risk abnormality cause data is given to the user end.

[0048] The risk elimination module is used to identify the risk characteristic factors corresponding to the risk abnormality cause data according to the output risk abnormality cause data, and retrieve the risk solution strategies associated with each risk characteristic factor from the database to form a risk solution strategy set corresponding to the output risk abnormality cause data. In this embodiment, the corresponding risk solution strategy is determined by identifying each risk characteristic factor corresponding to the risk abnormality cause data, which greatly improves the efficiency of quickly determining the risk solution strategy.

[0049] The point management module is used to visually manage sensors and devices in each laboratory in the building and on each device in the laboratory.

[0050] The point management module includes:

[0051] A selection matching module is used to identify the selected device corresponding to the feedback information according to the feedback information corresponding to the user end, and match all sensors and corresponding sensor data under the selected device from the database according to the selected device;

[0052] The data display module is used to generate a corresponding trend analysis chart based on the selected device, all sensors under the selected device and the corresponding sensor data, based on a preset trend screening strategy, and feed it back to the corresponding user end.

[0053] The preset trend screening strategy is:

[0054] Determine the screening type corresponding to this screening according to the selected device and all sensors under the selected device and the corresponding sensor data, and screen the sensor data according to the screening type; the screening type includes time screening and point screening;

[0055] If the filter type is time filter, the time period corresponding to this filter is determined, and the sensor data corresponding to each sensor corresponding to the time period is selected;

[0056] If the screening type is point screening, the sensor corresponding to this screening is determined, and the sensor data corresponding to the determined sensor is selected;

[0057] According to the selected sensor data, based on the preset trend screening rule set, the trend screening rule corresponding to this calculation is selected, the trend calculation is performed on the corresponding sensor data through the selected trend screening rule, and the calculation result is converted into a trend analysis chart. In this embodiment, the trend screening rule set includes multiple trend screening rules, such as the ratio of abnormal and normal sensors, the sensor abnormality rate, the number of sensor abnormalities and days, etc.

[0058] Embodiment 2

[0059] Compared with the first embodiment, the difference of this embodiment is that: the preset range in the risk identification module is dynamically changed and is related to the risk level value. Specifically, according to the sensor data with risks identified and the operation data corresponding to the abnormal equipment, based on the preset risk level value calculation strategy, the corresponding risk level value is calculated;

[0060] The risk level value calculation strategy is:

[0061] According to the sensor data with risks and the operation data of the equipment with abnormalities, the first risk value corresponding to the corresponding sensor data and the second risk value corresponding to the equipment are identified; the specific identification logic is:

[0062]

[0063] In the formula, S i is the first risk value of the i-th risky sensor data, x i is the value corresponding to the i-th risky sensor data, mix i is the first threshold of the sensor corresponding to the i-th risky sensor data, max i is the second threshold of the sensor corresponding to the i-th sensor data with risk, A, B, and C are the corresponding dynamically changing risk values, where A <B<C。

[0064]

[0065] Where D j is the second risk value corresponding to the jth abnormal device, Y j is the operating value of the operating data corresponding to the jth abnormal device, bj is the operating standard value corresponding to the jth abnormal device;

[0066] According to the first risk value and the second risk value, a corresponding risk level value is calculated based on a preset risk level calculation formula;

[0067] The risk level calculation formula is:

[0068]

[0069] In the formula, R is the risk level, w ij is the correlation between the i-th sensor data and the j-th device operation data, that is, the corresponding weight coefficient, α is the dynamic adjustment coefficient; M is the total number of sensor data with risks, and N is the total number of device operation data with abnormalities;

[0070] The preset range is dynamically adjusted according to the calculated risk level value, and the risk level value is positively correlated with the size of the preset range.

[0071] In this embodiment, by identifying the first risk value and the second risk value, the risk level of each sensor data and device operation data can be more finely evaluated. In the process of calculating the first risk value, multi-level classification is performed, that is, by setting three risk values ​​A, B, and C, which can more accurately reflect the abnormality of the data.

[0072] In the process of calculating the risk level value, by setting the weight coefficient, the risk level value can be dynamically adjusted according to the correlation between the sensor data and the equipment operation data. By setting the dynamic adjustment coefficient, the calculation result of the risk level value can be dynamically adjusted according to the actual situation. By considering multiple factors, the risk assessment strategy can be flexibly configured to adapt to different application scenarios. By dynamically adjusting the preset range, the risk status of the equipment can be identified and responded to in a timely manner.

[0073] The above is only an embodiment of the present invention. The common sense such as the known specific structure and characteristics in the scheme is described too much here. The ordinary technicians in the relevant field know all the common technical knowledge in the technical field of the invention before the application date or priority date, can know all the existing technologies in the field, and have the ability to apply the conventional experimental means before that date. The ordinary technicians in the relevant field can improve and implement this scheme in combination with their own abilities under the enlightenment given by this application. Some typical known structures or known methods should not become obstacles for ordinary technicians in the relevant field to implement this application. It should be pointed out that for those skilled in the art, without departing from the structure of the present invention, several deformations and improvements can be made, which should also be regarded as the scope of protection of the present invention, which will not affect the effect of the implementation of the present invention and the practicality of the patent. The scope of protection required by this application shall be based on the content of its claims, and the specific implementation methods and other records in the specification can be used to interpret the content of the claims.

Claims

1. Laboratory equipment operation monitoring system, characterized by: Including server and user side; The server includes: A deployment module is used to deploy sensors in various laboratories in the building and on various equipment in the laboratories; The data acquisition module is used to acquire the sensor data collected by each sensor; it is also used to collect the operation data corresponding to each device in the laboratory; The risk judgment module is used to judge whether each sensor data has risks based on the sensor data collected by each sensor, and identify the sensor data with risks; it is also used to judge whether the operating status of each device in each laboratory is abnormal based on the operating data corresponding to each device in each laboratory, and identify the abnormal device; A risk identification module is used to obtain sensor data of other sensors within a preset range and operating data of other devices based on the identified sensor data with risks and operating data corresponding to the equipment with abnormalities, and input the sensor data with risks, operating data corresponding to the equipment with abnormalities, and sensor data of other sensors within the preset range and operating data of other devices as input data into a preset risk identification model, and output corresponding risk abnormality cause data; The association module is used to associate the output risk abnormality cause data with the corresponding sensor or device and send it to the corresponding user end.

2. The laboratory equipment operation monitoring system according to claim 1, characterized in that: The server also includes: The risk elimination module is used to identify the various risk characteristic factors corresponding to the risk abnormality cause data based on the output risk abnormality cause data, and retrieve the risk resolution strategies associated with each risk characteristic factor from the database to form a risk resolution strategy set corresponding to the output risk abnormality cause data.

3. The laboratory equipment operation monitoring system according to claim 2, characterized in that: The server also includes: The point management module is used to visually manage sensors and devices in each laboratory in the building and on each device in the laboratory.

4. The laboratory equipment operation monitoring system according to claim 3, characterized in that: The point management module includes: A selection matching module is used to identify the selected device corresponding to the feedback information according to the feedback information corresponding to the user end, and match all sensors and corresponding sensor data under the selected device from the database according to the selected device; The data display module is used to generate a corresponding trend analysis chart based on the selected device, all sensors under the selected device and the corresponding sensor data, based on a preset trend screening strategy, and feed it back to the corresponding user end.

5. The laboratory equipment operation monitoring system according to claim 4, characterized in that: The preset trend screening strategy is: Determine the screening type corresponding to this screening according to the selected device and all sensors under the selected device and the corresponding sensor data, and screen the sensor data according to the screening type; the screening type includes time screening and point screening; If the screening type is time screening, the time period corresponding to this screening is determined, and the sensor data corresponding to each sensor corresponding to the time period is selected; If the screening type is point screening, the sensor corresponding to this screening is determined, and the sensor data corresponding to the determined sensor is selected; According to the selected sensor data, based on the preset trend screening rule set, the trend screening rule corresponding to this calculation is selected, the trend calculation is performed on the corresponding sensor data through the selected trend screening rule, and the calculation result is converted into a trend analysis chart.

Images