CN117555226B - Laboratory automation oriented center management system and method - Google Patents
Laboratory automation oriented center management system and method Download PDFInfo
- Publication number
- CN117555226B CN117555226B CN202410044237.3A CN202410044237A CN117555226B CN 117555226 B CN117555226 B CN 117555226B CN 202410044237 A CN202410044237 A CN 202410044237A CN 117555226 B CN117555226 B CN 117555226B
- Authority
- CN
- China
- Prior art keywords
- data
- equipment
- representing
- experimental
- module
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title abstract description 10
- 238000007726 management method Methods 0.000 claims abstract description 67
- 238000011217 control strategy Methods 0.000 claims abstract description 16
- 238000012545 processing Methods 0.000 claims abstract description 10
- 238000010801 machine learning Methods 0.000 claims description 26
- 238000012544 monitoring process Methods 0.000 claims description 24
- 230000003044 adaptive effect Effects 0.000 claims description 15
- 230000008859 change Effects 0.000 claims description 12
- 238000007405 data analysis Methods 0.000 claims description 12
- 238000002474 experimental method Methods 0.000 claims description 12
- 230000006870 function Effects 0.000 claims description 12
- 230000009897 systematic effect Effects 0.000 claims description 9
- 238000006243 chemical reaction Methods 0.000 claims description 8
- 238000005516 engineering process Methods 0.000 claims description 6
- 230000002159 abnormal effect Effects 0.000 claims description 4
- 238000012549 training Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 abstract description 5
- 238000013500 data storage Methods 0.000 abstract 1
- 230000006872 improvement Effects 0.000 description 8
- 238000004458 analytical method Methods 0.000 description 5
- 230000000007 visual effect Effects 0.000 description 3
- 230000002401 inhibitory effect Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000004989 laser desorption mass spectroscopy Methods 0.000 description 2
- 230000010355 oscillation Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000004801 process automation Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Abstract
The invention relates to a laboratory middle station management system, in particular to a laboratory automation oriented middle station management system and a laboratory automation oriented middle station management method. The device comprises a data acquisition unit, a data storage unit and a data processing unit, wherein the data acquisition unit is used for acquiring equipment data and experimental data and storing the acquired data into a database, and the database is used for storing sample data, experimental data, equipment data and user data; the dynamic decision unit is used for reading the acquired real-time data in the database, adjusting experimental parameters and optimizing experimental flow based on the PID control model, coordinating each instrument and robot device in the laboratory by adopting a dynamic cooperative control strategy, and issuing task scheduling instructions. Through PID control model and dynamic cooperative control strategy, the efficient, accurate and automatic operation of the laboratory is ensured, errors caused by human factors in the experimental process are reduced, and the working efficiency of the laboratory is greatly improved.
Description
Technical Field
The invention relates to a laboratory middle station management system, in particular to a laboratory automation oriented middle station management system and a laboratory automation oriented middle station management method.
Background
With the development and application of the internet of things technology, laboratory automation and intellectualization have become hot topics in research and industry; the internet of things provides possibility for data interaction and sharing among laboratory devices, so that the problem of long-term data island is expected to be solved; however, although the technology of internet of things brings new opportunities for laboratory automation, in practical applications, a series of challenges are still faced.
The LIMS system in the market at present mainly aims at sample management in a laboratory and provides the functions of tracking, storing, inquiring and the like of samples; the ELN system is mainly used for recording and managing experimental data and providing an electronic experimental note function; while LES systems focus on the control of the operation of experiments, such as sample processing, instrument control, etc.
Although these systems have met with some success in their respective fields, the degree of automation in the laboratory is still limited due to the lack of efficient data interaction and integration between them; for example, when sample data in a LIMS system needs to be analyzed in an ELN system, researchers often need to manually import or input the data, which not only increases the complexity of the operation, but may also introduce human error.
In summary, although some progress has been made in some aspects, the prior art solution still cannot meet the requirement of laboratory full-process automation, and because the laboratory automation degree of the prior art system is low, the prior art system may not be flexible enough to process different parameter ranges, dynamic changes or different time steps, and in view of this, a laboratory automation oriented central management system and method are provided.
Disclosure of Invention
The invention aims to provide a laboratory automation oriented intermediate management system and a laboratory automation oriented intermediate management method, so as to solve the problem that the laboratory automation degree of the existing system is low, and the laboratory automation degree is possibly inflexible under the condition of processing different parameter ranges, dynamic changes or different time steps.
To achieve the above object, in one aspect, the present invention provides a laboratory automation oriented central management system, including:
the data acquisition unit is used for acquiring equipment data and experimental data and storing the acquired data into a database, and the database is used for storing sample data, experimental data, equipment data and user data;
a dynamic decision unit for reading the real-time data stored in the database, adjusting experimental parameters and optimizing experimental flow based on the PID control model, coordinating each instrument and robot in the laboratory by adopting a dynamic cooperative control strategy, issuing task scheduling instructions,
the dynamic cooperative control strategy specifically comprises the following steps:
；
wherein,representation->Is indicative of the parameter ∈>Changes over time; />Actual parameters representing the PID; />Representing a learning rate for controlling a speed and an amplitude of parameter updating; />Representing a systematic error, representing a systematic output +.>A difference from the desired output; />Representing error->Relative to parameter->Is a partial derivative of (2); />Representation->、/>Or->One or more parameters of (a) a; />Representing the proportion of the PID controller; />Representing an integral of the PID controller; />A derivative parameter representing the PID controller;
in order to cope with the non-stationarity data, an adaptive learning rate is introduced, and the adaptive learning rate is specifically:
；
wherein,is indicated at the time step->Is a learning rate of (a); />Representing an initial learning rate; />Is indicated at the time step->Error->Relative to parameter->Is a partial derivative of (2); />Representing a constant; />Representation pair->From 1 to->Summing all of the terms of (a);
the device regulation and control unit is used for scheduling the instrument device and the robot device based on the task scheduling instruction issued by the dynamic decision unit;
the user authority management unit is used for verifying the user identity and ensuring that only authorized users operate;
the device monitoring and alarming unit is used for monitoring all device states in a laboratory in real time and giving an alarm in time when the device is abnormal; the equipment monitoring and alarming unit comprises an alarming module, wherein the alarming module analyzes the state of equipment by utilizing monitoring data of the sensor module and the monitoring module in the data acquisition unit and applying a preset rule or threshold value, and when abnormal or exceeding the preset range is monitored, the alarming module triggers an alarming system and generally sends alarming information to related personnel in an alarming sound, visual prompt or system notification mode.
As a further improvement of the technical scheme, the data acquisition unit comprises a sensor module, a monitoring module and a sample management module;
the sensor module is used for recording state data of the robot, state data of automatic equipment and reaction device data in real time;
the monitoring module adopts a distributed video stream processing technology and is used for real-time video monitoring of laboratories and equipment;
the sample management module is used for collecting sample data, recording information such as storage state and validity period of the sample in real time, tracking key data such as use state and calibration date of an analysis instrument, and carrying out structured storage and management on the sample data.
As a further improvement of the technical scheme, the database comprises a sample database, a user database, a log database, a document database and a device information database.
As a further improvement of the technical scheme, the dynamic decision unit comprises a data analysis module and a coordination and distribution module;
the data analysis module is used for analyzing and processing equipment data and experimental data acquired in real time based on a PID control model, identifying modes and trends in the experimental process and providing parameter adjustment suggestions based on the PID control model;
and the coordination distribution module formulates an experiment flow and issues task scheduling instructions to each instrument device and each robot device according to the data analysis result and the experiment requirement.
As a further improvement of the technical scheme, the PID control model is a machine learning model established based on an adaptive control algorithm and is used for carrying out cooperative operation on instruments and robot equipment in a laboratory, and the specific allocation steps are as follows:
s5.1, extracting and storing sample data, experimental data and equipment data from a database for PID control and input of a machine learning model;
s5.2, building and training a machine learning model based on historical data in a database, and predicting an optimal control strategy;
s5.3, according to the output of the machine learning model, adjusting PID parameters based on a dynamic cooperative control strategy, updating parameters of a PID controller, and calculating the output quantity of the controller by using the updated PID parameters;
s5.4, according to output of the PID controller, coordinating and controlling instruments and robot equipment in a laboratory through the equipment regulation and control unit.
As a further improvement of the present technical solution, in S5.2, the input data of the machine learning model isThe parameters of the predicted PID controller of the machine learning model are expressed as +.>The specific function model of the machine learning model established based on the adaptive control algorithm is as follows:
；
wherein,parameters representing a predicted PID controller; />A function representing a machine learning model for inputting +.>Conversion to PID parameter>Is a predicted value of (2); />Representing error term, representing model predictive value +.>And (3) the actual value->Differences between them.
ThenThe expression of (2) is specifically:
；
wherein,parameters representing a predicted PID controller; />Representing input features including historical data, real-time data, and device data; />Representing the weights of the model.
As a further improvement of the present technical solution, in S5.3, the PID parameter is adjusted based on a dynamic cooperative control policy, and the dynamic adjustment rule of the PID parameter is specifically:
；
wherein,representation->Is indicative of the parameter ∈>Changes over time; />Actual parameters representing the PID; />Representing a learning rate for controlling a speed and an amplitude of parameter updating; />Representing a systematic error, representing a systematic output +.>A difference from the desired output; />Representing error->Relative to parameter->Is a partial derivative of (2); by means of partial derivatives->Dynamically adjusting the parameters->Make systematic error->When the system changes, parameters of the PID controller can be correspondingly adjusted so as to better adapt to the system changes and improve the control performance; />Representation->、/>Or->One or more parameters of (a) a;
the fixed learning rate may not be flexible enough to handle different parameter ranges, dynamic changes or different time steps, and cannot adapt to the situation that the distribution characteristics of the data in time change, and in order to cope with the non-stationarity data, the self-adaptive learning rate is introduced, which specifically is:
；
wherein,is indicated at the time step->Is a learning rate of (a); />Representing an initial learning rate; />Is indicated at the time step->Error->Relative to parameter->Is a partial derivative of (2); />Representing a constant; />Representation pair->From 1 to->Summing all of the terms of (a);
the learning rate is adaptively adjusted according to the condition of parameter updating, parameter change and change of data characteristics are more flexibly adapted, the learning rate can be dynamically adjusted according to the condition of parameter adjustment by the adaptive learning rate, and the learning rate can be adjusted by calculating the square sum of partial derivatives of past errors, so that the parameter updating has different rates on different parameters and time steps, the adjustment condition of different parameters can be more effectively adapted, and the control performance is improved;
meanwhile, the output quantity of the controller is calculated by using the updated PID parameters, and the PID control model is specifically:
；
wherein,an input signal to the system representing the output of the controller, the PID controller; />Representing the error of the system, the difference between the expected value and the actual value; />The proportion of the PID controller is represented, and the proportion part is used for controlling errors and has influence on the response speed of the system; />The integral of the PID controller is represented and used for controlling the integral error and eliminating the steady-state error; />And the differential parameter of the PID controller is used for controlling the error change rate, improving the stability of the system and inhibiting the oscillation.
As a further improvement of the technical scheme, the equipment regulation and control unit comprises a scheduling module and a regulation and control module;
the scheduling module is used for receiving task scheduling instructions issued by the dynamic decision unit and making an optimized scheduling plan of experimental tasks according to the requirements of experiments and the availability of equipment;
the regulation and control module receives the task instruction from the scheduling module, communicates with the experimental equipment and the robot equipment, sends the task instruction to the experimental equipment and the robot equipment, receives the instruction and executes corresponding operation.
As a further improvement of the technical scheme, the user authority management unit comprises an identity verification module, an authority management module and an access control module;
the authentication module is used for verifying the identity authenticity of the user, the authenticated user authorizes the operation range of the user to the system according to the authority level of the user through the access control module, and the authority management module is used for managing and distributing the access authority of the user.
On the other hand, the invention provides a laboratory automation oriented center management method, which is based on the laboratory automation oriented center management system and comprises the following steps:
s10.1, acquiring equipment data and experimental data through a data acquisition unit, and storing the acquired data into a database;
s10.2, analyzing equipment data and experimental data acquired in real time by a dynamic decision unit based on a PID control model, and making an experimental flow and issuing task scheduling instructions to each instrument and each robot equipment according to a data analysis result and experimental requirements;
s10.3, receiving a task scheduling instruction issued by the dynamic decision unit through the equipment regulation and control unit, making an optimized scheduling plan of the experimental task according to the experimental requirement, communicating with the experimental equipment and the robot equipment through the regulation and control module, and sending the task instruction to the experimental equipment and the robot equipment;
s10.4, verifying and identifying the user information according to the user authority management unit, and distributing and managing the user authority through the authority management module to limit the user to access specific contents and functions.
Compared with the prior art, the invention has the beneficial effects that:
1. in the laboratory automation-oriented center management system and method, data acquisition, processing, instrument control and robot equipment control are integrated, and compared with the existing isolated laboratory management system, the laboratory automation-oriented center management system not only eliminates the problem of data island, but also can realize accurate control of instruments and robot equipment in a laboratory; aiming at the problem of manual operation errors and synergy between devices in the prior art, the invention ensures the efficient, accurate and automatic operation of a laboratory through a PID control model and a dynamic cooperative control strategy, reduces errors caused by human factors in the experimental process, greatly improves the working efficiency of the laboratory, and meets the urgent requirements of modern laboratories on the efficiency, the accuracy and the automation.
2. In the laboratory automation oriented central management system and method, PID parameters are adjusted based on a dynamic cooperative control strategy, so that parameters of a PID controller can be correspondingly adjusted when a system error changes, thereby better adapting to the change of the system and improving the control performance;
the adaptive learning rate is introduced for dealing with non-stationarity data, the learning rate can be adaptively adjusted according to the condition of parameter updating, parameter change and change of data characteristics can be more flexibly adapted, so that the parameter updating has different rates on different parameters and time steps, the adjustment condition of different parameters can be more effectively adapted, and the control performance is improved.
Drawings
Fig. 1 is an overall flow diagram of the present invention.
The meaning of each reference sign in the figure is:
1. a data acquisition unit; 2. a database; 3. a dynamic decision unit; 4. an equipment regulation and control unit; 5. a user authority management unit; 6. and the equipment monitoring and alarming unit.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1:
referring to fig. 1, a laboratory automation oriented central management system is provided, and includes a data acquisition unit 1, where the data acquisition unit 1 is configured to acquire device data and experiment data, and store the acquired data in a database 2, where the database 2 is configured to store sample data, experiment data, device data, and user data, and the database 2 includes a sample database, a user database, a log database, a document database, and a device information database, and the sample database is configured to store sample data and analysis results; the user database stores user information and authority data, the log database is used for storing operation logs and equipment state logs, and the document database is used for storing laboratory documents and version data; the equipment information database is used for storing the state data of the robot, the state data of the automation equipment and the reaction device data acquired by the sensor module;
further, the data acquisition unit 1 comprises a sensor module, a monitoring module and a sample management module; the sensor module is used for recording state data of the robot in real time, wherein the state data of the robot comprise running state, position and task data of the robot in real time; the automatic equipment state data comprises the running state, fault information and working time of the automatic equipment; reaction device data, wherein the reaction device data comprise sensor data for acquiring temperature, humidity, gas concentration and the like of a reaction device in real time;
the monitoring module adopts a distributed video stream processing technology, is used for real-time video monitoring of laboratories and equipment, realizes rapid retrieval of video data at any moment through video metadata indexing, provides monitoring visual angles in various forms by utilizing a multi-mode video analysis technology, meets the requirements of different scenes, monitors and displays video pictures of the laboratories and the equipment in real time, and supports multi-camera switching;
the sample management module is used for collecting sample data, recording information such as storage state and validity period of the sample in real time, tracking key data such as use state and calibration date of an analysis instrument, and carrying out structured storage and management on the sample data.
The laboratory automation oriented center management system further comprises a dynamic decision unit 3, wherein the dynamic decision unit 3 is used for reading real-time data stored in the database 2, adjusting experimental parameters and optimizing experimental flows based on a PID control model, coordinating various instrument devices and robot devices in a laboratory by adopting a dynamic cooperative control strategy, and issuing task scheduling instructions;
in this embodiment, the dynamic decision unit 3 includes a data analysis module and a coordination and allocation module;
the data analysis module is used for analyzing and processing equipment data and experimental data acquired in real time based on the PID control model, identifying modes and trends in the experimental process and providing parameter adjustment suggestions based on the PID control model;
and the coordination distribution module formulates an experiment flow and issues task scheduling instructions to each instrument device and each robot device according to the data analysis result and the experiment requirement.
The laboratory automation oriented center management system further comprises an equipment regulation and control unit 4, the equipment regulation and control unit 4 is used for scheduling the instrument equipment and the robot equipment based on the task scheduling instruction issued by the dynamic decision unit 3, and the equipment regulation and control unit 4 comprises a scheduling module and a regulation and control module;
the scheduling module is used for receiving task scheduling instructions issued by the dynamic decision unit 3, making an optimal scheduling plan of experimental tasks according to the requirements of experiments and the availability of equipment, optimizing resource utilization, avoiding conflict or resource waste among the equipment and improving the utilization rate of laboratory equipment to the greatest extent;
the regulation and control module receives the task instruction from the scheduling module, communicates with the experimental equipment and the robot equipment, sends the task instruction to the experimental equipment and the robot equipment, receives the instruction and executes corresponding operation, and can be used for controlling the start and stop of each equipment and the scheduling of the equipment, and a user can schedule the working sequence and time of the equipment according to experimental requirements.
The laboratory automation oriented central management system also comprises a user authority management unit 5, wherein the user authority management unit 5 is used for verifying the user identity and ensuring that only authorized users operate; the user authority management unit 5 comprises an identity verification module, an authority management module and an access control module; the authentication module is used for verifying the identity authenticity of a user, the authenticated user authorizes the operation range of the system according to the authority level of the authenticated user through various authentication means such as user name and password, double-factor authentication and fingerprint identification, the authority management module is used for managing and distributing the access authority of the user, the users at different levels can only access and operate the authorized content and the authorized function, the hierarchical management of the user authority is realized, and the security of the data is ensured.
The laboratory-oriented automation center management system further comprises an equipment monitoring and alarming unit 6, wherein the equipment monitoring and alarming unit 6 is used for monitoring all equipment states in a laboratory in real time and giving an alarm in time when the equipment is abnormal; the device monitoring and alarming unit 6 comprises an alarming module, the alarming module analyzes the state of the device by utilizing the monitoring data of the sensor module and the monitoring module in the data acquisition unit 1 and applying a preset rule or threshold value, and when the condition that the abnormality or the condition exceeds a preset range is monitored, the alarming module can trigger an alarming system to send alarming information to related personnel usually through an alarming sound, a visual prompt or a system notification mode.
The PID control model is a machine learning model established based on an adaptive control algorithm and is used for carrying out cooperative operation on instruments and robot equipment in a laboratory, the PID control model is a mixed model combining the machine learning model and the adaptive control algorithm so as to realize a more intelligent and more adaptive control system, the mixed model aims at predicting optimal PID parameters or control strategies by utilizing the machine learning capacity, and the PID parameters are dynamically adjusted according to real-time data by combining the adaptive control algorithm so as to realize more accurate and more flexible control, and the specific allocation steps are as follows:
s5.1, extracting and storing sample data, experimental data and equipment data from the database 2 for PID control and input of a machine learning model;
s5.2, building and training a machine learning model based on historical data in the database 2, and predicting an optimal control strategy;
in the present embodiment, the input data of the machine learning model is，/>Parameters of the predicted PID controller representing the history data, real-time data and device data of the machine learning model are expressed as +.>The specific function model of the machine learning model established based on the adaptive control algorithm is as follows:
；
wherein,parameters representing a predicted PID controller; />A function representing a machine learning model for inputting +.>Conversion to PID parameter>Is a predicted value of (2); />Representing error term, representing model predictive value +.>And (3) the actual value->Differences between them.
ThenThe expression of (2) is specifically:
；
wherein,parameters representing a predicted PID controller; />Representing input features including historical data, real-time data, and device data; />Representing the weights of the model.
S5.3, according to the output of the machine learning model, adjusting PID parameters based on a dynamic cooperative control strategy, updating parameters of a PID controller, and calculating the output quantity of the controller by using the updated PID parameters;
in this embodiment, if the PID parameters are adjusted based on the dynamic cooperative control policy, the dynamic adjustment rule of the PID parameters is specifically:
；
wherein,representation->Is indicative of the parameter ∈>Changes over time; />Actual parameters representing the PID; />Representing a learning rate for controlling a speed and an amplitude of parameter updating; />Representing a systematic error, representing a systematic output +.>A difference from the desired output; />Representing error->Relative to parameter->Is a partial derivative of (2); by means of partial derivatives->Dynamically adjusting the parameters->Make systematic error->When the system changes, parameters of the PID controller can be correspondingly adjusted so as to better adapt to the system changes and improve the control performance; />Representation->、/>Or->One or more parameters of (a) a;
the fixed learning rate may not be flexible enough to handle different parameter ranges, dynamic changes or different time steps, and cannot adapt to the situation that the distribution characteristics of the data in time change, and in order to cope with the non-stationarity data, the self-adaptive learning rate is introduced, which specifically is:
；
wherein,is indicated at the time step->Is a learning rate of (a); />Representing an initial learning rate; />Is indicated at the time step->Error->Relative to parameter->Is a partial derivative of (2); />Representing a constant->Is a very small constant for avoiding zero divisor; />Representation pair->From 1 to->Summing all of the terms of (a);
the learning rate is adaptively adjusted according to the parameter updating condition, so that the parameter change and the change of the data characteristic are more flexibly adapted; the self-adaptive learning rate can be dynamically adjusted according to the parameter adjustment condition, and the learning rate can be adjusted by calculating the square sum of partial derivatives of past errors, so that parameter updating has different rates on different parameters and time steps, the self-adaptive learning rate can be more effectively adapted to the adjustment condition of different parameters, and the control performance is improved;
meanwhile, the output quantity of the controller is calculated by using the updated PID parameters, and the PID control model is specifically:
；
wherein,an input signal to the system representing the output of the controller, the PID controller; />Representing the error of the system, the difference between the expected value and the actual value; />The proportion of the PID controller is represented, and the proportion part is used for controlling errors and has influence on the response speed of the system; />The integral of the PID controller is represented and used for controlling the integral error and eliminating the steady-state error; />And the differential parameter of the PID controller is used for controlling the error change rate, improving the stability of the system and inhibiting the oscillation.
S5.4, according to output of the PID controller, coordinating and controlling instruments and robot equipment in a laboratory through the equipment regulation and control unit 4.
Example 2:
the difference between the embodiment 2 and the embodiment 1 of the invention is that the embodiment is introduced to a static mechanical property acquisition analysis method used by a laboratory automation oriented center management system.
The laboratory automation oriented center management method is based on the laboratory automation oriented center management system and comprises the following steps:
s10.1, acquiring equipment data and experimental data through a data acquisition unit 1, and storing the acquired data into a database 2;
s10.2, analyzing equipment data and experimental data acquired in real time by a dynamic decision unit 3 based on a PID control model, making an experimental flow and issuing task scheduling instructions to each instrument equipment and each robot equipment according to a data analysis result and experimental requirements;
s10.3, receiving a task scheduling instruction issued by the dynamic decision unit 3 through the equipment regulation and control unit 4, making an optimized scheduling plan of an experimental task according to the experimental requirement, communicating with the experimental equipment and the robot equipment through the regulation and control module, and transmitting the task instruction to the experimental equipment and the robot equipment;
s10.4, verifying and identifying the user information according to the user authority management unit 5, and distributing and managing the user authority through the authority management module to limit the user to access specific contents and functions.
The foregoing has shown and described the basic principles, principal features and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the above-described embodiments, and that the above-described embodiments and descriptions are only preferred embodiments of the present invention, and are not intended to limit the invention, and that various changes and modifications may be made therein without departing from the spirit and scope of the invention as claimed. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (10)
1. A laboratory automation oriented central management system comprising:
the data acquisition unit (1) is used for acquiring equipment data and experimental data, and storing the acquired data into the database (2), wherein the database (2) is used for storing sample data, experimental data, equipment data and user data;
the dynamic decision unit (3), the said dynamic decision unit (3) is used for reading the real-time data stored in database (2), adjust the experimental parameter and optimize the experimental flow based on PID control model, adopt the dynamic cooperative control strategy to coordinate each instrument apparatus and robot apparatus in the laboratory, and issue the task and dispatch the instruction;
the dynamic cooperative control strategy specifically comprises the following steps:
；
wherein,representation->Is a rate of change of (2); />Actual parameters representing the PID; />Representing a learning rate; />Representing a systematic error; />Representing error->Relative to parameter->Is a partial derivative of (2); />Representation->、/>Or->One or more parameters of (a) a; />Representing the proportion of the PID controller; />Representing an integral of the PID controller; />A derivative parameter representing the PID controller;
in order to cope with the non-stationarity data, an adaptive learning rate is introduced, and the adaptive learning rate is specifically:
；
wherein,is indicated at the time step->Is a learning rate of (a); />Representing an initial learning rate; />Is indicated at the time step->Error->Relative to parameter->Is a partial derivative of (2); />Representing a constant; />Representation pair->From 1 to->Summing all of the terms of (a);
the device regulation and control unit (4), the device regulation and control unit (4) schedules the instrument device and the robot device based on the task scheduling instruction issued by the dynamic decision unit (3);
a user rights management unit (5), the user rights management unit (5) being adapted to verify the identity of a user and to ensure that only authorized users operate;
the equipment monitoring and alarming unit (6) is used for monitoring all equipment states in a laboratory in real time and giving an alarm in time when the equipment is abnormal.
2. Laboratory automation oriented central management system according to claim 1, characterized in that the data acquisition unit (1) comprises a sensor module, a monitoring module and a sample management module;
the sensor module is used for recording state data of the robot, state data of automatic equipment and reaction device data in real time;
the monitoring module adopts a distributed video stream processing technology and is used for real-time video monitoring of laboratories and equipment;
the sample management module is used for collecting sample data.
3. Laboratory automation oriented central management system according to claim 2, characterized in that the database (2) comprises a sample database, a user database, a log database, a document database and a device information database.
4. Laboratory automation oriented central management system according to claim 3, characterized in that the dynamic decision unit (3) comprises a data analysis module, a coordination allocation module;
the data analysis module is used for analyzing and processing equipment data and experimental data acquired in real time based on a PID control model;
and the coordination distribution module formulates an experiment flow and issues task scheduling instructions to each instrument device and each robot device according to the data analysis result and the experiment requirement.
5. The laboratory automation oriented central management system of claim 4, wherein the PID control model is a machine learning model established based on an adaptive control algorithm for collaborative operation of laboratory instruments and robotic devices, and the specific deployment steps are as follows:
s5.1, extracting stored sample data, experimental data and equipment data from a database (2) for PID control and input of a machine learning model;
s5.2, establishing and training a machine learning model based on historical data in the database (2) for predicting an optimal control strategy;
s5.3, according to the output of the machine learning model, adjusting PID parameters based on a dynamic cooperative control strategy, updating parameters of a PID controller, and calculating the output quantity of the controller by using the updated PID parameters;
s5.4, coordinating and controlling instruments and robot equipment in a laboratory through the equipment regulation and control unit (4) according to output of the PID controller.
6. The laboratory automation oriented central management system of claim 5, wherein in S5.2, the input data of the machine learning model isThe parameters of the predicted PID controller of the machine learning model are expressed as +.>The specific function model of the machine learning model established based on the adaptive control algorithm is as follows:
；
wherein,parameters representing a predicted PID controller; />A function representing a machine learning model; />Representing an error term;
thenThe expression of (2) is specifically:
；
wherein,parameters representing a predicted PID controller; />Representing the characteristics of the input;representing the weights of the model.
7. The laboratory automation oriented central management system according to claim 6, wherein in S5.3, the output of the controller is calculated using the updated PID parameters, and the PID control model is specifically:
；
wherein,representing the output of the controller; />Representing errors in the system; />Representing the proportion of the PID controller;representing an integral of the PID controller; />Representing the derivative parameters of the PID controller.
8. Laboratory automation oriented central management system according to claim 7, characterized in that the device regulation unit (4) comprises a scheduling module, a regulation module;
the scheduling module is used for receiving task scheduling instructions issued by the dynamic decision unit (3), and making an optimal scheduling plan of experimental tasks according to the requirements of experiments and the availability of equipment;
the regulation and control module receives the task instruction from the scheduling module, communicates with the experimental equipment and the robot equipment, sends the task instruction to the experimental equipment and the robot equipment, receives the instruction and executes corresponding operation.
9. Laboratory automation oriented central management system according to claim 8, characterized in that the user rights management unit (5) comprises an authentication module, a rights management module and an access control module;
the authentication module is used for verifying the identity authenticity of the user, the authenticated user authorizes the operation range of the user to the system according to the authority level of the user through the access control module, and the authority management module is used for managing and distributing the access authority of the user.
10. Laboratory automation oriented central management method based on the laboratory automation oriented central management system according to claim 9, characterized in that it comprises the following steps:
s10.1, acquiring equipment data and experimental data through a data acquisition unit (1), and storing the acquired data into a database (2);
s10.2, analyzing equipment data and experimental data acquired in real time by a dynamic decision unit (3) based on a PID control model, making an experimental flow and issuing task scheduling instructions to each instrument equipment and each robot equipment according to a data analysis result and experimental requirements;
s10.3, receiving a task scheduling instruction issued by the dynamic decision unit (3) through the equipment regulation and control unit (4), making an optimal scheduling plan of an experimental task according to the experimental requirement, and communicating with the experimental equipment and the robot equipment through the regulation and control module to send the task instruction to the experimental equipment and the robot equipment;
s10.4, verifying and identifying the user information according to the user authority management unit (5), and distributing and managing the user authority through the authority management module to limit the user to access specific contents and functions.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410044237.3A CN117555226B (en) | 2024-01-12 | 2024-01-12 | Laboratory automation oriented center management system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410044237.3A CN117555226B (en) | 2024-01-12 | 2024-01-12 | Laboratory automation oriented center management system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117555226A CN117555226A (en) | 2024-02-13 |
| CN117555226B true CN117555226B (en) | 2024-03-12 |
Family
ID=89815183
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410044237.3A Active CN117555226B (en) | 2024-01-12 | 2024-01-12 | Laboratory automation oriented center management system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117555226B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2010022391A2 (en) * | 2008-08-22 | 2010-02-25 | Azte Arizona Technology Enterprises | Integrated, automated system for the study of cell and tissue function |
| CN103021223A (en) * | 2012-11-22 | 2013-04-03 | 无锡南理工科技发展有限公司 | Intelligent training system for Internet of Things |
| CN110222891A (en) * | 2019-05-31 | 2019-09-10 | 广州仪速安电子科技有限公司 | A kind of wisdom laboratory ecosystem |
| CN114740765A (en) * | 2022-02-15 | 2022-07-12 | 北京恒世利德科技有限公司 | Intelligent safety monitoring system applied to laboratory |
| CN115963282A (en) * | 2022-12-15 | 2023-04-14 | 中国科学院大连化学物理研究所 | Hydrogen storage material evaluation laboratory automation platform and evaluation test method thereof |
-
2024
- 2024-01-12 CN CN202410044237.3A patent/CN117555226B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2010022391A2 (en) * | 2008-08-22 | 2010-02-25 | Azte Arizona Technology Enterprises | Integrated, automated system for the study of cell and tissue function |
| CN103021223A (en) * | 2012-11-22 | 2013-04-03 | 无锡南理工科技发展有限公司 | Intelligent training system for Internet of Things |
| CN110222891A (en) * | 2019-05-31 | 2019-09-10 | 广州仪速安电子科技有限公司 | A kind of wisdom laboratory ecosystem |
| CN114740765A (en) * | 2022-02-15 | 2022-07-12 | 北京恒世利德科技有限公司 | Intelligent safety monitoring system applied to laboratory |
| CN115963282A (en) * | 2022-12-15 | 2023-04-14 | 中国科学院大连化学物理研究所 | Hydrogen storage material evaluation laboratory automation platform and evaluation test method thereof |
Non-Patent Citations (2)
| Title |
|---|
| Shengwang Ye 等.Design and Implementation of a Novel Compact Laboratory for Web-Based Multiagent System Simulation and Experimentation.IEEE Transactions on Industrial Informatics.2023,全文. * |
| 吴峥 等.基于物联网的智慧实验室.《中国通信学会.第十七届全国青年通信学术年会论文集.国防工业出版社》.2012,全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117555226A (en) | 2024-02-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Hellerstein et al. | Feedback control of computing systems | |
| Granderson et al. | Building energy information systems: State of the technology and user case studies | |
| US7647131B1 (en) | Dynamic determination of sampling rates | |
| US8046096B2 (en) | Analytical server integrated in a process control network | |
| CN1119730C (en) | Apparatus used in production course and equipment including said apparatus and its simulated operation method | |
| US20100275147A1 (en) | Industrial energy demand management and services | |
| CN112817299A (en) | Industrial wastewater treatment data management cloud platform and control method thereof | |
| Piotrowski | Two‐Level Multivariable Control System of Dissolved Oxygen Tracking and Aeration System for Activated Sludge Processes | |
| Junker et al. | Towards industry 4.0 in corporate energy management | |
| CN117555226B (en) | Laboratory automation oriented center management system and method | |
| CN115439003A (en) | Gas meter replacement prompting method and system based on intelligent gas Internet of things | |
| CN107942873B (en) | A kind of the operation cost intelligence accounting and monitoring method of Furniture manufacture production line | |
| Faggioli et al. | System effect estimation by sharding: A comparison between anova approaches to detect significant differences | |
| Liu et al. | Two perishable inventory systems with one-way substitution | |
| Parto et al. | Cyber-physical system implementation for manufacturing with analytics in the cloud layer | |
| Priore et al. | Learning-based scheduling of flexible manufacturing systems using support vector machines | |
| Garpinger | Design of robust PID controllers with constrained control signal activity | |
| CN113723668A (en) | Coal blending method, system, equipment and storage medium based on robust optimization | |
| CN117092956A (en) | Gas flowmeter valve control linkage control method, system and equipment based on Internet of things | |
| CN114740765A (en) | Intelligent safety monitoring system applied to laboratory | |
| CN113282356B (en) | Method, system and storage medium for executing local distributed analysis in real time | |
| US20210292704A1 (en) | Method and system for cell operations using artificial intelligence | |
| Veronica | Automatically detecting faulty regulation in HVAC controls | |
| CN115271318A (en) | Energy recovery scheduling method and device | |
| CN112785425A (en) | Distributed intelligent economic management system and management method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |