Laboratory monitoring and alarm system and method based on internet of things

Abstract

The application discloses a laboratory monitoring alarm system and method based on the Internet of Things, relates to the technical field of laboratory monitoring alarm, and comprises the following steps: constructing a monitoring alarm cloud platform, analyzing the environment approximation degree between a laboratory and a historical laboratory, evaluating the standard data of the monitoring indexes of a characteristic historical laboratory, and obtaining the abnormal monitoring data according to the environment fitting degree of the characteristic historical laboratory; acquiring the abnormal monitoring data of the characteristic historical laboratory of the laboratory, performing abnormality evaluation on the monitoring indexes in the laboratory according to the abnormal monitoring data, obtaining target monitoring indexes, acquiring the historical monitoring records of the characteristic historical laboratory, optimizing and adjusting the standard data of the target monitoring indexes in the laboratory, and obtaining target standard data; acquiring the target standard data of the laboratory, performing safety monitoring on the laboratory in a current period, performing abnormality evaluation on the laboratory in combination with the target standard data, and performing intelligent alarm on the laboratory.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of laboratory monitoring alarm, in particular to a laboratory monitoring alarm system and method based on Internet of Things. BACKGROUND

[0002] At present, the use of Internet of Things technology has become more and more common in the field of laboratory safety monitoring. The use of Internet of Things technology brings benefits to the laboratory monitoring alarm system, including but not limited to the following: 1. Real-time data monitoring. The application of Internet of Things technology enables monitoring devices to collect and transmit data in a timely manner, and the data obtained can reflect the current state of the laboratory in real time, thereby achieving timely warning and reducing safety hazards. 2. Remote management. Through Internet of Things technology, laboratory managers can monitor the laboratory status at any time and anywhere. 3. Automation and intelligence of early warning. Internet of Things can realize automatic control and management, and the monitoring alarm system can automatically trigger alarms and execute preset response measures, reducing manual intervention.

[0003] At present, the monitoring alarm in the laboratory is mainly to monitor the environment of the laboratory by the monitoring device, and to evaluate the abnormality of the laboratory according to the threshold value of the environmental data obtained by the monitoring device. However, in actual situations, the environment and layout of the laboratory are different, which may cause the preset monitoring data threshold to deviate from the actual situation of the laboratory, resulting in false alarms or delayed alarms. This not only affects the normal work of the laboratory, but also may cause safety accidents in the laboratory, causing huge losses. SUMMARY

[0004] The purpose of the present application is to provide a laboratory monitoring alarm system and method based on Internet of Things to solve the problems in the prior art.

[0005] To achieve the above purpose, the present application provides the following technical solution: a laboratory monitoring alarm method based on Internet of Things, the method comprising:

[0006] Step S100: constructing a monitoring alarm cloud platform, obtaining experimental environment data of the laboratory, obtaining historical experimental environment data of the historical laboratory, analyzing the environmental approximation degree between the laboratory and the historical laboratory, and obtaining a characteristic historical laboratory;

[0007] Step S200: obtaining the historical abnormal alarm records and the historical safety accident records of the characteristic historical laboratory, obtaining the standard data of the monitoring indicators of the characteristic historical laboratory from the cloud platform, evaluating the standard data of the monitoring indicators of the characteristic historical laboratory, and obtaining the abnormal monitoring data according to the environmental fit degree of the characteristic historical laboratory;

[0008] Step S300: Obtain the characteristic history laboratory of the laboratory, the abnormal monitoring data of the laboratory, and evaluate the abnormality of the monitoring index in the laboratory according to the abnormal monitoring data, obtain the target monitoring index, obtain the history monitoring record of the characteristic history laboratory, and optimize and adjust the standard data of the target monitoring index in the laboratory to obtain the target standard data.

[0009] Step S400: Obtain the target standard data of the laboratory, and perform safety monitoring on the laboratory in the current period, and combine the target standard data to evaluate the abnormality of the laboratory, and intelligently alarm the laboratory.

[0010] Further, step S100 includes:

[0011] Step S101: Obtain the experimental environment data of the laboratory, which includes the data corresponding to each environmental parameter of the laboratory, and obtain the historical experimental environment data of each historical laboratory from the cloud platform, which includes the data corresponding to each environmental parameter of the historical laboratory.

[0012] Step S102: Obtain the average value of each environmental parameter of the historical laboratory, and obtain the mark value of each environmental parameter of the historical laboratory, wherein the mark value Xa of the ath environmental parameter of the historical laboratory is a :

[0013] ,

[0014] Wherein, C a is the average value of the ath environmental parameter in the historical laboratory; C´ a is the average value of the ath environmental parameter in each historical laboratory and the laboratory; σ a is the standard deviation of the average value of the ath environmental parameter in each historical laboratory and the laboratory.

[0015] Step S103: Based on the mark value of each environmental parameter of the historical laboratory, a characteristic vector X of the historical laboratory is constructed, X={X1, X2, X3,..., Xn}, wherein X1, X2, X3,..., Xn respectively represent the mark value of the 1st, 2nd, 3rd,..., nth environmental parameter in the historical laboratory. n n

[0016] Step S104: Analyze the environmental approximation degree between the laboratory and each historical laboratory, wherein the specific process of analyzing the environmental approximation degree between the laboratory and the dth historical laboratory is as follows:

[0017] Calculate the environmental approximation score β d ​​:

[0018] ,

[0019] wherein, X d represents the feature vector of the dth historical laboratory; Y represents the feature vector of the laboratory;

[0020] Step S105: when the environment approximation score β d is greater than the preset approximation score threshold, it is determined that the dth historical laboratory is similar to the laboratory in environment, and the dth historical laboratory is recorded as the characteristic historical laboratory of the laboratory.

[0021] Further, step S200 comprises:

[0022] Step S201: the characteristic historical laboratory of the laboratory is acquired, the historical abnormal alarm record of the characteristic historical laboratory is acquired, the historical abnormal alarm data is acquired from the historical abnormal alarm record, and the historical abnormal alarm data is the maximum value of the monitoring index triggering the alarm;

[0023] Step S202: the preset standard data of the monitoring index of the characteristic historical laboratory is acquired from the cloud platform, and the standard data is the preset threshold value of the monitoring index;

[0024] Step S203: each historical abnormal alarm record of the characteristic historical laboratory is acquired, when the maximum value of a certain monitoring index of a certain historical abnormal alarm record in the characteristic historical laboratory is greater than the threshold value of the certain monitoring index, the certain historical abnormal alarm record is recorded as the characteristic historical abnormal alarm record of the certain monitoring index;

[0025] Step S204: the preset threshold value of each monitoring index of the characteristic historical laboratory is calculated, and the first characteristic environment fit degree of the characteristic historical laboratory, wherein the preset threshold value of the dth monitoring index of the characteristic historical laboratory is calculated, and the first characteristic environment fit degree of the characteristic historical laboratory is L d :

[0026] ,

[0027] wherein, M d represents the total number of the characteristic historical abnormal alarm records of the dth monitoring index in the characteristic historical laboratory; M sum represents the total number of each historical abnormal alarm record in the characteristic historical laboratory;

[0028] Step S205: when the first characteristic environment fit degree L dIf the first characteristic environment fitting degree threshold is less than the preset first characteristic environment fitting degree threshold, it is determined that the preset threshold of the dth monitoring index is not fitted with the characteristic historical laboratory environment, and the preset threshold of the dth monitoring index triggers a characteristic historical laboratory error alarm, and the dth monitoring index is marked as the first abnormal monitoring index of the characteristic historical laboratory.

[0029] In step S206, the historical security incident record of the characteristic historical laboratory is obtained from the cloud platform, and historical security incident data is extracted from the historical security incident record. The historical security incident data is the data corresponding to each monitoring index in the characteristic historical laboratory when the characteristic historical laboratory has a security incident. The first abnormal monitoring index of the characteristic historical laboratory is excluded from each monitoring index, and a plurality of monitoring indexes of the characteristic historical laboratory are obtained.

[0030] In step S207, the characteristic value of the plurality of monitoring indexes in the historical security incident record is calculated. The characteristic proportion value F e =G e，max / Q e of the e th monitoring index in the historical security incident record is calculated, where G e，max represents the maximum value of the e th monitoring index in the characteristic historical laboratory in the historical security incident record, and Q e represents the threshold value of the e th monitoring index.

[0031] In step S208, when the characteristic proportion value of the e th monitoring index is greater than the preset characteristic proportion threshold, the historical security incident record is recorded as the characteristic historical security incident record of the e th monitoring index.

[0032] In step S209, the second characteristic environment fitting degree H e =K e / K sum of the preset threshold of the e th monitoring index and the characteristic historical laboratory is calculated, where K sum represents the total number of historical security incident records of the characteristic historical laboratory, and K e represents the total number of characteristic historical security incident records of the e th monitoring index in the characteristic historical laboratory.

[0033] In step S210, when the second characteristic environment fitting degree H e is greater than the preset second characteristic environment fitting degree threshold, it is determined that the preset threshold of the e th monitoring index is not fitted with the characteristic historical laboratory environment, and the threshold value of the e th monitoring index cannot be used as a determination condition for the environmental abnormality of the characteristic historical laboratory. The e th monitoring index is marked as the second abnormal monitoring index of the characteristic historical laboratory.

[0034] Step S211: Obtain the first abnormal monitoring index and the second abnormal monitoring index of the characteristic historical laboratory, and aggregate to obtain the abnormal monitoring data of the characteristic historical laboratory;

[0035] The generation of the record of the abnormal alarm in the characteristic historical laboratory in the above step is because the preset threshold does not conform to the actual situation of the characteristic historical laboratory. If the threshold is set too small, the actual abnormality of the characteristic historical laboratory does not occur, but the alarm is still issued. The historical safety accident record indicates that the monitoring index in the characteristic historical laboratory does not appear to be greater than the preset threshold, but the safety accident occurs in the characteristic historical laboratory, indicating that the monitoring index is set too large, so that the abnormality of the characteristic historical laboratory cannot be accurately judged. Therefore, obtaining the abnormal monitoring index in the characteristic historical laboratory from the two aspects not only makes the obtained data more accurate, but also makes the data more comprehensive, which is helpful for subsequent abnormal judgment of the monitoring index of the laboratory.

[0036] Further, step S300 includes:

[0037] Step S301: Obtain the abnormal monitoring data of each characteristic historical laboratory of the laboratory, and perform abnormality evaluation on each monitoring index of the laboratory. The process of performing abnormality evaluation on the βth monitoring index in the laboratory includes:

[0038] Obtain the total number U' of the characteristic historical laboratories whose βth monitoring index is the first abnormal monitoring index β Obtain the total number U'' of the characteristic historical laboratories whose βth monitoring index is the second abnormal monitoring index β Calculate the index abnormality score P of the βth monitoring index in the laboratory β :

[0039] ,

[0040] Wherein, γ1 represents a preset first characteristic coefficient; γ2 represents a preset second characteristic coefficient, γ1+γ2=1; U sum represents the total number of each characteristic historical laboratory of the laboratory;

[0041] Step S302: When the index abnormality score P β is greater than a preset index abnormality score threshold, it is determined that the βth monitoring index in the laboratory is abnormal, and the βth monitoring index is recorded as the target monitoring index of the laboratory;

[0042] Step S303: Obtain the standard data of the target monitoring index of the laboratory from the cloud platform, and optimize and adjust the standard data of the target monitoring index in the laboratory. The specific optimization and adjustment process is:

[0043] From each feature historical laboratory, a plurality of feature historical laboratories are obtained which have the same preset threshold value of the target monitoring index of the laboratory;

[0044] Step S304: Obtain each historical normal operation record of the plurality of feature historical laboratories, and obtain the mean value of the maximum value of the target monitoring index in the plurality of feature historical laboratories from each historical normal operation record, and record the mean value as the target threshold value of the target monitoring index in the laboratory;

[0045] Step S305: Obtain the target threshold value of the plurality of target monitoring indexes of the laboratory, and replace the preset threshold value of the plurality of target monitoring indexes in the standard data of the laboratory with the target threshold value of the plurality of target monitoring indexes to obtain the target standard data of the laboratory.

[0046] Further, step S400 comprises:

[0047] Step S401: Use the plurality of monitoring devices connected in network to monitor the laboratory in the current period to obtain the data of each monitoring index in the laboratory;

[0048] Step S402: Obtain the target standard data of the laboratory, and when there is a monitoring index whose value is greater than the threshold value in the target standard data among the monitoring indexes monitored by the monitoring device of the laboratory in the current period, determine that the laboratory is abnormal and intelligently alarm the laboratory.

[0049] In order to better realize the above method, a laboratory monitoring and alarming system based on Internet of Things is further provided, which comprises an environment approximation analysis module, a fitting evaluation module, a target standard data module, and an intelligent monitoring and alarming module;

[0050] The environment approximation analysis module is used to analyze the approximation degree between the laboratory and the historical laboratory to obtain the feature historical laboratory;

[0051] The fitting evaluation module is used to evaluate the fitting degree between the standard data of the monitoring index of the feature historical laboratory and the environment of the feature historical laboratory to obtain the abnormal monitoring data;

[0052] The target standard data module is used to evaluate the abnormality of the monitoring index of the laboratory to obtain the target monitoring index, and to optimize and adjust the standard data of the target monitoring index in the laboratory according to the historical monitoring record of the feature historical laboratory to obtain the target standard data;

[0053] The intelligent monitoring and alarming module is used to perform safety monitoring on the laboratory in the current period, evaluate the abnormality of the laboratory in combination with the target standard data, and intelligently alarm the laboratory.

[0054] Further, the environment approximation analysis module comprises an environment approximation scoring unit and an environment approximation analysis unit.

[0055] The environment approximation scoring unit is configured to calculate environment approximation scores between the laboratory and the historical laboratories.

[0056] The environment approximation analysis unit is configured to analyze the degree of environment approximation between the laboratory and each of the historical laboratories according to the environment approximation scores between the laboratory and each of the historical laboratories, and obtain a characteristic historical laboratory.

[0057] Further, the fit evaluation module comprises a historical data acquisition unit and a fit evaluation unit.

[0058] The historical data acquisition unit is configured to acquire historical abnormal alarm records of the characteristic historical laboratory, standard data of monitoring indicators of the characteristic historical laboratory from a cloud platform, and historical safety accident records of the characteristic historical laboratory.

[0059] The fit evaluation unit is configured to evaluate the degree of environment fit between the standard data of monitoring indicators of the characteristic historical laboratory and the characteristic historical laboratory, and obtain abnormal monitoring data of the characteristic historical laboratory.

[0060] Further, the target standard data module comprises an indicator abnormality scoring unit and a target standard data unit.

[0061] The indicator abnormality scoring unit is configured to calculate indicator abnormality scores of each monitoring indicator in the laboratory.

[0062] The target standard data unit is configured to evaluate abnormality of each monitoring indicator in the laboratory, obtain target monitoring indicators of the laboratory, and optimize and adjust standard data of the target monitoring indicators in the laboratory, to obtain target standard data of the laboratory.

[0063] Further, the intelligent monitoring and alarming module comprises an intelligent monitoring and alarming unit.

[0064] The intelligent monitoring and alarming unit is configured to monitor the laboratory in a current period, acquire data of each monitoring indicator in the laboratory, and intelligently alarm the laboratory.

[0065] Compared with the prior art, the present application has the beneficial effects that: the present application realizes intelligent monitoring and alarm of the laboratory, obtains a characteristic historical laboratory with similar environment by analyzing the similarity of the environment between the laboratory and the historical laboratory, and evaluates the threshold of each monitoring index in the characteristic historical laboratory, whether the characteristic historical laboratory can be accurately judged as abnormal, obtains abnormal monitoring data in the characteristic historical laboratory, evaluates whether the preset threshold of each monitoring index in the laboratory has a problem with the help of the abnormal monitoring data in the characteristic historical laboratory, and optimizes and adjusts the standard data of the target monitoring index in the laboratory in combination with the historical data of the characteristic historical laboratory, so that the preset monitoring index is highly consistent with the actual situation of the laboratory, greatly reduces the probability of false alarm and safety accidents in the laboratory, and ensures the safety of the laboratory. BRIEF DESCRIPTION OF DRAWINGS

[0066] Fig. 1 is a method flowchart of the laboratory monitoring and alarm system and method based on the Internet of Things of the present application;

[0067] Fig. 2 is a module schematic diagram of the laboratory monitoring and alarm system and method based on the Internet of Things of the present application. DETAILED DESCRIPTION

[0068] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0069] Embodiment: as shown in the present application provides a technical solution, a laboratory monitoring and alarm method based on the Internet of Things, the method comprising: Figs. 1-2

[0070] Step S100: constructing a monitoring and alarm cloud platform, obtaining experimental environment data of the laboratory, obtaining historical experimental environment data of the historical laboratory, analyzing the approximation degree of the environment between the laboratory and the historical laboratory, and obtaining a characteristic historical laboratory;

[0071] Among them, step S100 includes:

[0072] Step S101: obtaining the experimental environment data of the laboratory, the experimental environment data of the laboratory including data corresponding to each environmental parameter of the laboratory, obtaining the historical experimental environment data of each historical laboratory from the cloud platform, and the historical experimental environment data including data corresponding to each environmental parameter of the historical laboratory;

[0073] ​For example, the environmental parameters include laboratory temperature, laboratory humidity, etc.

[0074] Step S102: obtaining the average values of the environmental parameters of the historical laboratories, and obtaining the mark values of the environmental parameters in the historical laboratories, wherein the mark value Xaof the athenvironmental parameter in the historical laboratories is calculated according to the following formula: a :

[0075] ,

[0076] wherein C a represents the average value of the athenvironmental parameter in the historical laboratories; C´ a represents the average value of the athenvironmental parameter in each historical laboratory; σ a represents the standard deviation of the average value of the athenvironmental parameter in each historical laboratory;

[0077] Step S103: constructing the feature vector X={X1, X2, X3,...,Xn} of the historical laboratories based on the mark values of the environmental parameters in the historical laboratories, wherein X1, X2, X3,...,Xnrespectively represent the mark values of the 1st, 2nd, 3rd,...,nthenvironmental parameters in the historical laboratories. n n

[0078] Step S104: analyzing the environmental approximation degree between the laboratory and each historical laboratory, wherein the specific process of analyzing the environmental approximation degree between the laboratory and the dthhistorical laboratory is as follows:

[0079] calculating the environmental approximation score β d :

[0080] ,

[0081] wherein X d represents the feature vector of the dthhistorical laboratory; Y represents the feature vector of the laboratory.

[0082] Step S105: when the environmental approximation score β d is greater than a preset approximation score threshold, determining that the dthhistorical laboratory is environmentally approximated with the laboratory, and recording the dthhistorical laboratory as a characteristic historical laboratory of the laboratory.

[0083] ​​Step S200: obtaining the historical abnormal alarm record and the historical safety accident record of the feature historical laboratory, obtaining the standard data of the monitoring index of the feature historical laboratory from the cloud platform, evaluating the standard data of the monitoring index of the feature historical laboratory, and the degree of fit of the environment of the feature historical laboratory, to obtain abnormal monitoring data;

[0084] The step S200 comprises:

[0085] Step S201: obtaining the feature historical laboratory of the laboratory, obtaining the historical abnormal alarm record of the feature historical laboratory, obtaining the historical abnormal alarm data from the historical abnormal alarm record, and the historical abnormal alarm data is the maximum value of the monitoring index triggering the alarm;

[0086] Step S202: obtaining the preset standard data of the monitoring index of the feature historical laboratory from the cloud platform, and the standard data is the preset threshold value of the monitoring index;

[0087] Step S203: obtaining each historical abnormal alarm record of the feature historical laboratory, when the maximum value of a certain monitoring index of a certain historical abnormal alarm record in the feature historical laboratory is greater than the threshold value of the certain monitoring index, the certain historical abnormal alarm record is recorded as the feature historical abnormal alarm record of the certain monitoring index;

[0088] Step S204: calculating the preset threshold value of each monitoring index of the feature historical laboratory and the first feature environment fit degree of the feature historical laboratory, wherein the preset threshold value of the dth monitoring index of the feature historical laboratory and the first feature environment fit degree of the feature historical laboratory are represented as L d :

[0089] ,

[0090] Wherein, M d represents the total number of feature historical abnormal alarm records of the dth monitoring index in the feature historical laboratory; M sum represents the total number of each historical abnormal alarm record in the feature historical laboratory;

[0091] For example, the monitoring indexes include laboratory temperature, laboratory humidity, etc.

[0092] Step S205: when the first feature environment fit degree L d is less than the preset first feature environment fit threshold value, it is determined that the preset threshold value of the dth monitoring index is not fit with the environment of the feature historical laboratory, and the preset threshold value of the dth monitoring index will trigger false alarm of the feature historical laboratory, and the dth monitoring index is recorded as the first abnormal monitoring index of the feature historical laboratory;

[0093] Step S206: Obtain the historical safety accident record of the feature historical laboratory from the cloud platform, extract the historical safety accident data from the historical safety accident record, the historical safety accident data is the data corresponding to each monitoring index in the feature historical laboratory when the feature historical laboratory has a safety accident, remove the first abnormal monitoring index of the feature historical laboratory from each monitoring index to obtain several monitoring indexes of the feature historical laboratory;

[0094] Step S207: Calculate the feature value of the several monitoring indexes in the historical safety accident record, wherein the feature proportion value F e =G e，max / Q e , wherein G e，max represents the maximum value of the e-th monitoring index of the feature historical laboratory in the historical safety accident record, Q e represents the threshold value of the e-th monitoring index;

[0095] Step S208: When the feature proportion value of the e-th monitoring index is greater than the preset feature proportion threshold value, record the historical safety accident record as the feature historical safety accident record of the e-th monitoring index;

[0096] Step S209: Calculate the second feature environment fit degree H e =K e / K sum , wherein K sum represents the total number of the historical safety accident records of the feature historical laboratory, K e represents the total number of the feature historical safety accident records of the e-th monitoring index in the feature historical laboratory;

[0097] For example, the total number of the historical safety accident records of the feature historical laboratory K sum is 50, and the total number of the feature historical safety accident records of the second monitoring index in the feature historical laboratory K2 is 20;

[0098] The second feature environment fit degree H2 = 20 / 50 = 0.4 is calculated by taking the preset threshold value of the second monitoring index and the feature historical laboratory;

[0099] Step S210: When the second feature environment fit degree H e is greater than the preset second feature environment fit threshold value, it is determined that the preset threshold value of the e-th monitoring index is not fit for the environment of the feature historical laboratory, and the threshold value of the e-th monitoring index cannot be used as a determination condition of the environmental abnormality of the feature historical laboratory, and the e-th monitoring index is recorded as the second abnormal monitoring index of the feature historical laboratory;

[0100] Step S211: Obtain the first abnormal monitoring index and the second abnormal monitoring index of the characteristic historical laboratory, and aggregate to obtain the abnormal monitoring data of the characteristic historical laboratory;

[0101] Step S300: Obtain the abnormal monitoring data of the characteristic historical laboratory of the laboratory, and perform abnormality evaluation on the monitoring indexes in the laboratory according to the abnormal monitoring data to obtain a target monitoring index, obtain the historical monitoring record of the characteristic historical laboratory, and optimize and adjust the standard data of the target monitoring index in the laboratory to obtain target standard data;

[0102] The step S300 comprises:

[0103] Step S301: Obtain the abnormal monitoring data of each characteristic historical laboratory of the laboratory, and perform abnormality evaluation on each monitoring index of the laboratory, wherein the process of performing abnormality evaluation on the βth monitoring index in the laboratory comprises:

[0104] Obtain the total number U of the characteristic historical laboratories whose βth monitoring index is the first abnormal monitoring index β Obtain the total number U of the characteristic historical laboratories whose βth monitoring index is the second abnormal monitoring index β Calculate the index abnormal score P of the βth monitoring index in the laboratory β :

[0105] ,

[0106] Wherein, γ1 represents a preset first characteristic coefficient; γ2 represents a preset second characteristic coefficient, and γ1+γ2=1; U sum represents the total number of each characteristic historical laboratory of the laboratory;

[0107] For example, the total number U of the characteristic historical laboratories whose first monitoring index is the first abnormal monitoring index is 20; the total number U of the characteristic historical laboratories whose first monitoring index is the second abnormal monitoring index is 30; the total number of each characteristic historical laboratory U sum is 100; the first characteristic coefficient γ1 is 0.4; the second characteristic coefficient γ2 is 0.6;

[0108] Calculate the index abnormal score P1 of the first monitoring index in the laboratory:

[0109] ,

[0110] Step S302: When the index abnormal score P βIf the index is greater than the preset index abnormal score threshold, it is determined that the beta monitoring index in the laboratory is abnormal, and the beta monitoring index is recorded as the target monitoring index of the laboratory.

[0111] Step S303: Obtain the standard data of the target monitoring index of the laboratory from the cloud platform, and optimize and adjust the standard data of the target monitoring index in the laboratory. The specific optimization and adjustment process is as follows:

[0112] From each feature historical laboratory, obtain a plurality of feature historical laboratories with the same preset threshold value as the target monitoring index of the laboratory.

[0113] Step S304: Obtain each historical normal operation record of the plurality of feature historical laboratories, obtain the mean value of the maximum value of the target monitoring index in the plurality of feature historical laboratories from each historical normal operation record, and record the mean value as the target threshold value of the target monitoring index in the laboratory.

[0114] Step S305: Obtain the target threshold value of the plurality of target monitoring indexes of the laboratory, and replace the preset threshold value of the plurality of target monitoring indexes in the standard data of the laboratory with the target threshold value of the plurality of target monitoring indexes, to obtain the target standard data of the laboratory.

[0115] Step S400: Obtain the target standard data of the laboratory, perform safety monitoring on the laboratory in the current period, and perform abnormal evaluation on the laboratory in combination with the target standard data, and intelligently alarm the laboratory;

[0116] Step S400 includes:

[0117] Step S401: Use a plurality of monitoring devices connected to the Internet to monitor the laboratory in the current period, and obtain the data of each monitoring index in the laboratory.

[0118] Step S402: Obtain the target standard data of the laboratory, and when there is a monitoring index with a value greater than the threshold value in the target standard data among the monitoring indexes monitored by the monitoring devices in the laboratory in the current period, it is determined that the laboratory is abnormal, and the laboratory is intelligently alarmed.

[0119] In order to better realize the above method, a laboratory monitoring and alarm system based on the Internet of Things is also proposed. The system includes an environment approximation analysis module, a fitting evaluation module, a target standard data module, and an intelligent monitoring and alarm module.

[0120] The environment approximation analysis module is used to analyze the environment approximation degree between the laboratory and the historical laboratory, and obtain the feature historical laboratory.

[0121] The fitting evaluation module is configured to evaluate the fitting degree between the standard data of the monitoring indicators of the characteristic historical laboratory and the environment of the characteristic historical laboratory, and obtain abnormal monitoring data.

[0122] The target standard data module is configured to evaluate the abnormality of the monitoring indicators of the laboratory, obtain target monitoring indicators, and optimize and adjust the standard data of the target monitoring indicators of the laboratory according to the historical monitoring records of the characteristic historical laboratory, to obtain target standard data.

[0123] The intelligent monitoring and alarm module is configured to perform safety monitoring on the laboratory in the current period, evaluate the abnormality of the laboratory in combination with the target standard data, and intelligently alarm the laboratory.

[0124] The environment approximation analysis module includes an environment approximation scoring unit and an environment approximation analysis unit.

[0125] The environment approximation scoring unit is configured to calculate the environment approximation score between the laboratory and the historical laboratories.

[0126] The environment approximation analysis unit is configured to analyze the environment approximation degree between the laboratory and each of the historical laboratories according to the environment approximation scores between the laboratory and each of the historical laboratories, and obtain the characteristic historical laboratory.

[0127] The fitting evaluation module includes a historical data acquisition unit and a fitting evaluation unit.

[0128] The historical data acquisition unit is configured to acquire the historical abnormal alarm records of the characteristic historical laboratory, acquire the standard data of the monitoring indicators of the characteristic historical laboratory from the cloud platform, and acquire the historical safety accident records of the characteristic historical laboratory.

[0129] The fitting evaluation unit is configured to evaluate the fitting degree between the standard data of the monitoring indicators of the characteristic historical laboratory and the environment of the characteristic historical laboratory, and obtain abnormal monitoring data of the characteristic historical laboratory.

[0130] The target standard data module includes an indicator abnormality scoring unit and a target standard data unit.

[0131] The indicator abnormality scoring unit is configured to calculate the indicator abnormality score of each monitoring indicator in the laboratory.

[0132] The target standard data unit is configured to evaluate the abnormality of each monitoring indicator in the laboratory, obtain target monitoring indicators of the laboratory, and optimize and adjust the standard data of the target monitoring indicators in the laboratory, to obtain target standard data of the laboratory.

[0133] The intelligent monitoring and alarm module includes an intelligent monitoring and alarm unit.

[0134] The intelligent monitoring alarm unit is used for monitoring the laboratory in the current period, obtaining the data of various monitoring indexes in the laboratory, and intelligently alarming the laboratory.

[0135] It will be apparent to those skilled in the art that the application is not limited to the details of the above-exemplified embodiments and that the application can be implemented in other particular forms without departing from the spirit or essential characteristics of the application. The embodiments should therefore be considered in all respects as illustrative and not restrictive, the scope of the application being indicated by the appended claims rather than by the above description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. No reference signs in the claims should be considered as limiting the scope of the claims with respect to the figures in which the application is set forth.

Claims

1. A method for monitoring and alarming of a laboratory based on Internet of Things, characterized in that, The method comprises: Step S100: constructing a monitoring alarm cloud platform, acquiring experimental environment data of a laboratory, acquiring historical experimental environment data of a historical laboratory, analyzing the environment approximation degree between the laboratory and the historical laboratory, and obtaining a characteristic historical laboratory; Step S200: acquiring historical abnormal alarm records and historical safety accident records of the characteristic historical laboratory, acquiring standard data of monitoring indexes of the characteristic historical laboratory from the cloud platform, evaluating the standard data of the monitoring indexes of the characteristic historical laboratory, and obtaining abnormal monitoring data according to the environment fitting degree of the characteristic historical laboratory; Step S300: acquiring abnormal monitoring data of the characteristic historical laboratory of the laboratory, and performing abnormality evaluation on monitoring indexes in the laboratory according to the abnormal monitoring data to obtain target monitoring indexes, acquiring historical monitoring records of the characteristic historical laboratory, and optimizing and adjusting standard data of the target monitoring indexes in the laboratory to obtain target standard data; Step S400: acquiring the target standard data of the laboratory, performing safety monitoring on the laboratory in a current period, and performing abnormal evaluation on the laboratory in combination with the target standard data, and performing intelligent alarm on the laboratory.

2. The IoT based laboratory monitoring alarm method as claimed in claim 1 wherein, The step S100 comprises: Step S101: acquiring experimental environment data of a laboratory, the experimental environment data of the laboratory comprising data corresponding to various environmental parameters of the laboratory, acquiring historical experimental environment data of each historical laboratory from a cloud platform, and the historical experimental environment data comprising data corresponding to various environmental parameters of the historical laboratory; Step S102: obtaining the average value of each environmental parameter of the historical laboratory, and obtaining the mark value of each environmental parameter in the historical laboratory, wherein the mark value Xa of the ath environmental parameter in the historical laboratory is calculated according to the following formula: a : ， wherein C a represents the average value of the a-th environmental parameter in the history laboratory; C´ a represents the average value of the a-th environmental parameter in the history laboratory and in the laboratory; σ a represents the standard deviation of the average value of the a-th environmental parameter in the history laboratory and in the laboratory; Step S103: Based on the labeled values ​​of various environmental parameters in the historical laboratory, construct the feature vector X={X1, X2, X3, ..., X...} of the historical laboratory. n }, where X1, X2, X3, ..., X n These are respectively represented as the labeled values ​​of the 1st, 2nd, 3rd, ..., nth environmental parameters in the historical laboratory; Step S104: analyzing the environment approximation degree between the laboratory and each historical laboratory, wherein the specific process of analyzing the environment approximation degree between the laboratory and the dth historical laboratory is as follows: computing an environmental proximity score β between the laboratory and the dth historical laboratory d : ， where X d represents a feature vector for the dth historical lab; Y represents a feature vector for the lab; Step S105: When the environmental approximation score β d If the score is greater than the preset approximate scoring threshold, the environment of the d-th historical laboratory is determined to be similar to that of the laboratory, and the d-th historical laboratory is recorded as the characteristic historical laboratory of the laboratory.

3. The IoT based laboratory monitoring alarm method as claimed in claim 2 wherein, The step S200 comprises: Step S201: acquiring a characteristic historical laboratory of the laboratory, acquiring historical abnormal alarm records of the characteristic historical laboratory, and acquiring historical abnormal alarm data from the historical abnormal alarm records, the historical abnormal alarm data being a maximum value of a monitoring index triggering an alarm; Step S202: acquiring preset standard data of monitoring indexes of the characteristic historical laboratory from a cloud platform, the standard data being a preset threshold value of the monitoring index; Step S203: acquiring each historical abnormal alarm record of the characteristic historical laboratory, when a maximum value of a certain monitoring index in a certain historical abnormal alarm record of the characteristic historical laboratory is greater than a threshold value of the certain monitoring index, recording the certain historical abnormal alarm record as a characteristic historical abnormal alarm record of the certain monitoring index. Step S204: calculating the preset threshold of each monitoring index of the characteristic historical laboratory, and the first characteristic environment fitting degree of the characteristic historical laboratory, wherein the preset threshold of the dth monitoring index of the characteristic historical laboratory and the first characteristic environment fitting degree of the characteristic historical laboratory are L d : ， wherein M d represents the total number of feature history abnormal alarm records in the feature history laboratory as the dth monitoring index; sum represents the total number of each history abnormal alarm record in the feature history laboratory. Step S205: When the first characteristic environment fitting degree L d If the first characteristic environment fitting degree L is less than the preset first characteristic environment fitting degree threshold, it is determined that the preset threshold of the dth monitoring index is not fitted with the characteristic historical laboratory environment, and the preset threshold of the dth monitoring index will trigger the characteristic historical laboratory error alarm. The dth monitoring index is marked as the first abnormal monitoring index of the characteristic historical laboratory. Step S206: Obtain the historical safety accident record of the characteristic historical laboratory from the cloud platform, extract the historical safety accident data from the historical safety accident record, the historical safety accident data is the data corresponding to each monitoring index in the characteristic historical laboratory when the characteristic historical laboratory has a safety accident, and the first abnormal monitoring index of the characteristic historical laboratory is excluded from the monitoring index to obtain several monitoring indexes of the characteristic historical laboratory; Step S207: calculating the characteristic value of the several monitoring indexes in the historical safety accident record, wherein the characteristic proportion value F e =G e，max / Q e , wherein G e，max represents the maximum value of the e-th monitoring index of the characteristic historical laboratory in the historical safety accident record, Q e represents the threshold value of the e-th monitoring index. Step S208: When the characteristic proportion value of the e-th monitoring index is greater than the preset characteristic proportion threshold, the historical safety accident record is recorded as the characteristic historical safety accident record of the e-th monitoring index; Step S209: calculating the threshold value of the e-th monitoring index preset, and the second feature environment fitting degree H of the feature historical laboratory e =K e / K sum , wherein K sum represents the total number of historical safety accident records of the feature historical laboratory, K e represents the total number of feature historical safety accident records of the e-th monitoring index in the feature historical laboratory; Step S210: When the second characteristic environment fitting degree H e When the second characteristic environment fitting degree H is greater than the preset second characteristic environment fitting degree threshold, it is determined that the preset threshold of the e-th monitoring index does not fit the characteristic historical laboratory environment, and the threshold of the e-th monitoring index cannot be used as a determination condition of the environmental anomaly of the characteristic historical laboratory. The e-th monitoring index is recorded as a second abnormal monitoring index of the characteristic historical laboratory. Step S211: Obtain the first abnormal monitoring index and the second abnormal monitoring index of the characteristic historical laboratory, and collect them to obtain the abnormal monitoring data of the characteristic historical laboratory.

4. The IoT based laboratory monitoring alarm method as claimed in claim 3 wherein, The step S300 comprises: Step S301: Obtain the abnormal monitoring data of each characteristic historical laboratory of the laboratory, and perform abnormality evaluation on each monitoring index of the laboratory, wherein the process of performing abnormality evaluation on the β-th monitoring index in the laboratory comprises: obtaining a total number U' of characteristic historical laboratories in which the βth monitoring indicator is a first abnormal monitoring indicator β obtaining a total number U'' of characteristic historical laboratories in which the βth monitoring indicator is a second abnormal monitoring indicator β calculating an indicator abnormality score P of the βth monitoring indicator in the laboratory β : ， wherein γ1 represents a preset first characteristic coefficient; γ2 represents a preset second characteristic coefficient, and γ1 + γ2 = 1; U sum represents the total number of the respective characteristic history laboratories of the laboratory. Step S302: when the index abnormality score P β greater than a preset index abnormality score threshold, determining that the βth monitoring index in the laboratory has abnormality, and taking the βth monitoring index as a target monitoring index of the laboratory. Step S303: Obtain the standard data of the target monitoring index of the laboratory from the cloud platform, and perform optimization adjustment on the standard data of the target monitoring index of the laboratory, and the specific optimization adjustment process is: Obtain several characteristic historical laboratories with the same preset threshold value of the target monitoring index of the laboratory from the several characteristic historical laboratories; Step S304: Obtain each historical normal operation record of the several characteristic historical laboratories, obtain the mean value of the maximum value of the target monitoring index in the several characteristic historical laboratories from the several historical normal operation records, and record the mean value as the target threshold value of the target monitoring index in the laboratory; Step S305: Obtain the target threshold value of the several target monitoring indexes of the laboratory, and replace the preset threshold value of the several target monitoring indexes in the standard data of the laboratory with the target threshold value of the several target monitoring indexes to obtain the target standard data of the laboratory.

5. The IoT based laboratory monitoring alarm method as claimed in claim 4 wherein, The step S400 comprises: Step S401: Monitor the laboratory in the current period using the plurality of networked monitoring devices to obtain the data of each monitoring index in the laboratory; Step S402: Obtain the target standard data of the laboratory, when there is a monitoring index with a value greater than the threshold value in the target standard data among the monitoring indexes monitored by the monitoring devices of the laboratory in the current period, it is determined that the laboratory has an abnormality, and the laboratory is intelligently alarmed.

6. The laboratory monitoring and alarming system based on Internet of Things according to any one of claims 1-5, characterized in that, The system comprises an environment approximation analysis module, a fitting evaluation module, a target standard data module, and an intelligent monitoring alarm module; The environment approximation analysis module is configured to analyze the environment approximation degree between the laboratory and the historical laboratory to obtain the characteristic historical laboratory. The fitting evaluation module is configured to evaluate the fitting degree between the standard data of the monitoring indicators of the characteristic historical laboratory and the environment of the characteristic historical laboratory, to obtain abnormal monitoring data. The target standard data module is configured to evaluate the abnormality of the monitoring indicators of the laboratory, to obtain target monitoring indicators, and to optimize and adjust the standard data of the target monitoring indicators of the laboratory according to the historical monitoring records of the characteristic historical laboratory, to obtain target standard data. The intelligent monitoring and alarm module is configured to perform safety monitoring on the laboratory in the current period, to evaluate the abnormality of the laboratory in combination with the target standard data, and to intelligently alarm the laboratory.

7. The Internet of Things based laboratory monitoring and alarming system as claimed in claim 6, wherein, The environment approximation analysis module comprises an environment approximation scoring unit and an environment approximation analysis unit. The environment approximation scoring unit is configured to calculate the environment approximation scores between the laboratory and the historical laboratories. The environment approximation analysis unit is configured to analyze the environment approximation degrees between the laboratory and the historical laboratories according to the environment approximation scores between the laboratory and the historical laboratories, to obtain characteristic historical laboratories.

8. The laboratory monitoring alarm system based on Internet of Things as claimed in claim 6 wherein, The fitting evaluation module comprises a historical data acquisition unit and a fitting evaluation unit. The historical data acquisition unit is configured to acquire the standard data of the monitoring indicators of the characteristic historical laboratory from the cloud platform according to the historical abnormal alarm records of the characteristic historical laboratory and the historical safety accident records of the characteristic historical laboratory. The fitting evaluation unit is configured to evaluate the fitting degree between the standard data of the monitoring indicators of the characteristic historical laboratory and the environment of the characteristic historical laboratory, to obtain abnormal monitoring data of the characteristic historical laboratory.

9. The laboratory monitoring alarm system based on Internet of Things as claimed in claim 6 wherein, The target standard data module comprises an indicator abnormality scoring unit and a target standard data unit. The indicator abnormality scoring unit is configured to calculate the indicator abnormality scores of the monitoring indicators in the laboratory. The target standard data unit is configured to evaluate the abnormality of the monitoring indicators in the laboratory, to obtain target monitoring indicators of the laboratory, and to optimize and adjust the standard data of the target monitoring indicators in the laboratory, to obtain target standard data of the laboratory.

10. The laboratory monitoring alarm system based on Internet of Things as claimed in claim 6 wherein, The intelligent monitoring and alarm module comprises an intelligent monitoring and alarm unit. The intelligent monitoring and alarm unit is configured to monitor the laboratory in the current period, to acquire the data of the monitoring indicators in the laboratory, and to intelligently alarm the laboratory.

Images