Industrial remote collaboration system and method based on Internet of Things
Through an industrial remote collaboration system based on the Internet of Things, the combination of the Internet of Things device layer and data processing layer is used to realize remote monitoring and intelligent task scheduling of industrial sites, solving the problems of operator skills and safety hazards in industrial site maintenance work , improves work efficiency and safety.
Patent Information
- Application Number
- CN202411189785.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-28
- Publication Date
- 2024-11-19
- Estimated Expiration
- 2044-08-28
AI Technical Summary
In industrial sites, the maintenance and maintenance of electrical equipment faces challenges such as high experience and skills requirements, high safety risks, and complexity of the on-site environment, which makes it difficult for operators to deal with problems alone. It requires guidance from remote experts, but the existing collaboration tools are lacking Scalability and flexibility make it difficult to adapt to different needs and scenarios.
The industrial remote collaboration system based on the Internet of Things realizes vital sign monitoring and video transmission through the IoT device layer. The data transmission layer transmits on-site data in real time. The data processing layer performs data processing and analysis, providing decision support for remote guidance personnel, and through intelligence Task scheduling genetic algorithm adjusts task allocation to ensure work efficiency and security.
Remote monitoring and guidance of on-site operators has been realized, work efficiency and safety has been improved, losses caused by system error commands have been avoided, and the efficiency and safety of industrial cooperation has been significantly improved, providing efficient and intelligent for modern industrial production. Remote collaboration solutions.
Smart Images

Figure CN118691057B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of industrial collaboration technology, and specifically to an industrial remote collaboration system and method based on the Internet of Things. Background Art
[0002] With the rapid development of information technology, the Internet of Things (IoT) technology has demonstrated its great potential and value in many fields. Especially in the industrial field, the application of IoT technology has not only improved production efficiency, but also greatly improved work safety and quality. In recent years, with the rise of remote collaboration technology, industrial remote collaboration systems based on the Internet of Things have gradually become a research hotspot.
[0003] In industrial sites, the inspection and maintenance of electrical equipment often face many challenges. Traditional inspection methods often require on-site operators to have rich experience and skills, and the working environment may also have many safety hazards. In addition, due to the complexity and uncertainty of the industrial site environment, on-site operators often find it difficult to deal with all problems alone and need guidance and support from remote experts.
[0004] For example, the existing patent with publication number CN112558974A discloses a system, method and computer medium for collaborative development of industrial applications, including an industrial integrated development environment (IDE) supporting collaboration tools, which enable multiple designers and programmers to submit design inputs remotely to the same automation system project in parallel while maintaining project consistency. These collaboration features may include, for example: coordination between different sets of design inputs for the same part of a system project; generating notifications to remote designers when a part of a system project is modified; and sharing development interfaces or environments. However, as the project grows and the team changes, the collaboration tools may need to be highly scalable and flexible to adapt to different needs and scenarios. To this end, the present invention provides an industrial remote collaboration system and method based on the Internet of Things. Summary of the invention
[0005] The purpose of the present invention is to provide an industrial remote collaboration system and method based on the Internet of Things to solve the existing problems raised in the above background technology.
[0006] To achieve the above purpose, the present invention provides the following technical solutions: an industrial remote collaboration system based on the Internet of Things, which realizes real-time monitoring and video transmission of the vital signs of on-site operators through the Internet of Things device layer, transmits the on-site data to the remote guidance personnel in real time through the data transmission layer, and then processes and analyzes the received data by the data processing layer to provide decision support for the remote guidance personnel. This system can not only realize remote monitoring and guidance of on-site operators, but also intelligently adjust task allocation according to the actual situation of the operators, thereby effectively improving work efficiency and safety, including:
[0007] The IoT device layer is used to provide operators with vital signs monitoring bracelets and video transmission equipment; the data transmission layer is used to transmit the video of the electrical equipment maintenance site to the instructor's monitoring terminal through the video transmission equipment, connect the electrical equipment maintenance site and the instructor, and transmit the operator's vital signs to the central server through the vital signs monitoring bracelet; the data processing layer is used to receive and process the output data of the IoT device layer; the data storage layer is used to enter all instructions into the instruction database and store the output data in the data processing layer;
[0008] The data processing layer includes an instruction decision module, an operator ability monitoring module and a task allocation module; the instruction decision module is used to determine whether to operate according to the instruction issued by the instructor and the status of the electrical equipment. If the result is no, the system makes instruction suggestions by calculating the expected values of all instructions; the operator ability monitoring module is used to monitor the operator's reaction and adaptability to the instruction through the vital signs monitoring bracelet when the operator executes the instruction, and output it to the task allocation module; the task allocation module is used to create an intelligent task scheduling genetic algorithm, and adjust the task allocation according to the operator's reaction and adaptability, workload and current task progress under the instruction.
[0009] The present invention is further improved in that the instruction decision module includes an instruction potential result database establishment unit, an instruction expectation calculation unit, an electrical equipment status monitoring unit, an instruction expectation updating unit and an instruction judgment unit; the instruction potential result database establishment unit is used to assign potential probabilities to potential results caused by all instructions in the electrical equipment maintenance process, and the potential results include successful equipment repair, partial repair, repair failure and further damage; the instruction expectation calculation unit is used to quantify the potential result value and then calculate the initial instruction expectation of the instruction issued by the instructor; the electrical equipment status monitoring unit is used to calculate the electrical equipment danger value according to the current state of the electrical equipment; the instruction expectation updating unit is used to use the electrical equipment danger value as a weight factor to adjust the initial instruction expectation;
[0010] A further improvement of the present invention is that the operator capability monitoring module includes a vital signs monitoring unit and an evaluation model building unit, the vital signs monitoring unit is used to obtain the operator's current adaptation data, the adaptation data including heart rate stability, blood pressure change rate, reaction time and task completion quality; the evaluation model building unit is used to calculate the operator's reaction and adaptability to the instruction through the operator's adaptation data.
[0011] On the other hand, the present invention provides an industrial remote collaboration method based on the Internet of Things, comprising the following steps:
[0012] S1. The instructor issues an instruction based on the video data of the electrical equipment maintenance site, and the expected value of the instruction is calculated according to the instruction issued by the instructor and the state of the electrical equipment;
[0013] S2. Setting an instruction expectation threshold value. When the instruction expectation value is greater than or equal to the instruction expectation threshold value, the operator performs the operation according to the instruction issued by the instructor. When the instruction expectation value is less than the instruction expectation threshold value, the initial instruction expectation values of all instructions in the instruction database are calculated, and the maximum value is extracted as a new instruction to be transmitted to the operator.
[0014] S3. When the operator performs an operation instruction, the adaptation data of the operator under the instruction is monitored by the vital sign monitoring bracelet to obtain the personal ability value of the operator;
[0015] S4. Create an intelligent task scheduling genetic algorithm to adjust task allocation based on the personal ability values, workload and current task progress of all operators.
[0016] The present invention is further improved in that the specific step S1 comprises:
[0017] S11. Establish a potential result database of instructions, including a potential result probability sequence and a potential result value quantification sequence, to obtain initial instruction expectations;
[0018] S12. Calculate the hazard value of electrical equipment by the temperature and vibration amplitude frequency of the electrical equipment;
[0019] S13. Setting the danger threshold of electrical equipment , to update the initial instruction expectation and obtain the expected value of the instruction.
[0020] A further improvement of the present invention is that the potential result probability sequence includes the probabilities assigned by the system to the potential results caused by all instructions, The potential outcome probability sequence of an instruction is expressed as , represents the potential probability of successful repair, represents the potential probability of partial repair, represents the potential probability of repair failure, Represents the potential probability of further damage; the potential result value quantization sequence is expressed as , Indicates The quantitative value of a successful equipment repair, Indicates The quantified value of the partial repair of a piece of equipment, Indicates The quantitative value of a failed device repair, Indicates The quantitative value of further damage to the equipment; let the instruction issued by the supervisor be The device operated by the operator is the equipment, then the instructor is in the The initial instruction expectation calculation formula for each device is: .
[0021] A further improvement of the present invention is that the electrical equipment danger value is obtained by Equipment evenly installed A temperature sensor and collects time Inner The vibration amplitude data set and vibration velocity data set of the electrical equipment with the time interval are obtained. The calculation formula for the electrical equipment hazard value of each device is: , Indicates The average temperature of each device, Indicates Device time The average vibration amplitude of the internal equipment, Indicates Device time The average vibration velocity of the internal equipment, represents the temperature mean weight, represents the mean weight of the vibration amplitude, Represents the mean weight of vibration velocity.
[0022] A further improvement of the present invention is that the expected value calculation formula of the instruction is:
[0023] .
[0024] The present invention is further improved in that the specific steps of calculating the personal ability value include:
[0025] S31, recording the time when the operator starts the operation through the vital signs monitoring bracelet Until the end of the operation Every time Heart rate data set collected in and blood pressure dataset ,in Indicates Heart rate data, Indicates Blood pressure data, get heart rate stability and blood pressure change rate ,in, Represents the average value of the data in the heart rate data set;
[0026] S32. Record the time when the instruction was issued , get the operator's reaction time ;
[0027] S33, when the operation is finished, calculate the The electrical equipment hazard value of each device is used to obtain the second electrical equipment hazard value , then the task completion quality calculation formula is ;
[0028] S34. Calculate the operator's personal capability value by obtaining data through steps S31-S32:
[0029] ;
[0030] in, represents the weight of heart rate stability, represents the blood pressure change rate weight, represents the reaction time weight, Represents the task completion quality weight.
[0031] The present invention is further improved in that the specific steps of the intelligent task scheduling genetic algorithm include:
[0032] S41, for tasks to be assigned and Operators perform coding, using dimensional array represents the task assignment, where each value is in between;
[0033] S42. Randomly generate a population containing multiple task allocation schemes ,Each solution is an encoded task representation;
[0034] S43. Constructing fitness function ,in, Represents the weight of personal ability value, represents the task load weight, Indicates the task progress weight, Indicates the task load of the operator, which is obtained by recording the number of tasks remaining to be completed by the operator as the task load of the operator. Indicates the task progress of the operator, calculated by obtaining the standard completion time of the task , and get the current time in real time , get the task progress of the operator ;
[0035] S44, Select The task allocation scheme of the top 6 in fitness is used as the first population ;
[0036] S45, Random Selection The two task allocation schemes in are used as parent task allocation schemes, and a position is selected in the parent task allocation scheme for crossover operation to form a new child task allocation scheme;
[0037] S46. Set mutation probability , changing the element value in the new child task allocation scheme according to the mutation probability to form a second child task allocation scheme;
[0038] S47, repeat steps S44-S46, and calculate the fitness function of the new task allocation scheme;
[0039] S48, the results of all fitness functions are included in the fitness sequence. When the standard deviation of the data in the fitness sequence is less than the set fitness fluctuation threshold, the iteration is stopped and the task allocation plan at this time is output.
[0040] A further improvement of the present invention is that the mutation probability is obtained by using the initial mutation probability , personal ability variation value and fitness improvement threshold are obtained; when the individual's personal ability value is greater than the personal ability variation value, the variation probability is updated, and the calculation formula is: ,in represents an attenuation factor, , k represents the number of iterations at this time; when the individual's personal ability value is less than or equal to the personal ability variation value, it is judged whether the fitness of the individual in the genetic process is less than the fitness improvement threshold for three consecutive times. If it is judged as yes, the variation probability is increased by 50 times, if it is judged as no, the initial variation probability is returned.
[0041] Compared with the prior art, the present invention has the following beneficial effects:
[0042] 1. The present invention firstly monitors the vital signs and task execution of operators to evaluate their personal ability values, and accordingly uses an intelligent task scheduling genetic algorithm to dynamically allocate tasks to ensure balanced workload and efficient completion of tasks;
[0043] 2. Secondly, the present invention also establishes a database of potential results of instructions, and through remote collaboration between instructors and operators, calculates the danger value of electrical equipment and updates the initial instruction expectations, further improving the efficiency and safety of remote collaboration;
[0044] 3. Through the intelligent task scheduling genetic algorithm in the task allocation module, task allocation can be flexibly adjusted according to the operator's response and adaptability, workload and current task progress, thereby improving overall operation efficiency;
[0045] 4. By setting the instruction expectation threshold, when the instruction expectation value is greater than or equal to the instruction expectation threshold, the operator operates according to the instructions issued by the instructor; when the instruction expectation value is less than the instruction expectation threshold, the initial instruction expectation values of all instructions in the instruction database are calculated, and the maximum value is extracted as a new instruction to be transmitted to the operator, thereby realizing real-time remote monitoring of the industrial site while avoiding losses caused by system erroneous instructions. Moreover, through intelligent evaluation and scheduling, the efficiency and safety of industrial collaboration are significantly improved, providing an efficient and intelligent remote collaboration solution for modern industrial production. BRIEF DESCRIPTION OF THE DRAWINGS
[0046] Figure 1 The framework diagram of the industrial remote collaboration system based on the Internet of Things disclosed in the present invention is shown;
[0047] Figure 2 The flowchart of the industrial remote collaboration method based on the Internet of Things disclosed in the present invention is shown;
[0048] Figure 3 The specific steps of the intelligent task scheduling genetic algorithm of the industrial remote collaboration method based on the Internet of Things disclosed in the present invention are demonstrated. DETAILED DESCRIPTION
[0049] The technical solution of the present invention is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present invention and the specific features in the embodiments are detailed descriptions of the technical solution of the present invention, rather than limitations on the technical solution of the present invention. The embodiments of the present invention and the technical features in the embodiments may be combined with each other unless there is a conflict.
[0050] The term "and / or" is only a way to describe the association relationship of related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " generally indicates that the related objects are in an "or" relationship.
[0051] Example 1
[0052] Figure 1 The framework diagram of the industrial remote collaboration system based on the Internet of Things disclosed in this embodiment is shown, including:
[0053] The IoT device layer is used to provide operators with vital signs monitoring bracelets and video transmission equipment; the data transmission layer is used to transmit the video of the electrical equipment maintenance site to the instructor's monitoring terminal through the video transmission equipment, connect the electrical equipment maintenance site and the instructor, and transmit the operator's vital signs to the central server through the vital signs monitoring bracelet; the data processing layer is used to receive and process the output data of the IoT device layer; the data storage layer is used to enter all instructions into the instruction database and store the output data in the data processing layer; the data processing layer includes an instruction decision module, an operator capability monitoring module and a task allocation module;
[0054] The instruction decision module is used to determine whether to operate according to the instruction issued by the instructor and the state of the electrical equipment. If the result is no, the system will make instruction suggestions by calculating the expected values of all instructions; it includes an instruction potential result database establishment unit, an instruction expectation calculation unit, an electrical equipment state monitoring unit, an instruction expectation update unit and an instruction judgment unit; the instruction potential result database establishment unit is used to assign potential probabilities to the potential results caused by all instructions in the electrical equipment maintenance process, and the potential results include successful equipment repair, partial repair, repair failure and further damage; the instruction expectation calculation unit is used to quantify the potential result value and then calculate the initial instruction expectation of the instruction issued by the instructor; the electrical equipment state monitoring unit is used to calculate the electrical equipment danger value according to the current state of the electrical equipment; the instruction expectation update unit is used to use the electrical equipment danger value as a weight factor to adjust the initial instruction expectation of the instruction issued by the instructor;
[0055] The operator capability monitoring module is used to monitor the operator's reaction and adaptability to the instruction through the vital signs monitoring bracelet when the operator executes the instruction, and output it to the task allocation module; the operator capability monitoring module includes a vital signs monitoring unit and an evaluation model establishment unit, the vital signs monitoring unit is used to obtain the operator's current adaptation data, and the adaptation data includes heart rate stability, blood pressure change rate, reaction time and task completion quality; the evaluation model establishment unit is used to calculate the operator's reaction and adaptability to the instruction through the operator adaptation data.
[0056] The task allocation module is used to create an intelligent task scheduling genetic algorithm to adjust the task allocation according to the operator's reaction and adaptability, workload and current task progress under the instruction.
[0057] Example 2
[0058] Figure 2 The flowchart of the industrial remote collaboration method based on the Internet of Things in this embodiment is shown. Based on the same inventive concept as that in Embodiment 1, the present invention provides an industrial remote collaboration method based on the Internet of Things, comprising the following steps:
[0059] S1. The instructor issues an instruction based on the video data of the electrical equipment maintenance site, and calculates the instruction expected value of the instruction based on the instruction issued by the instructor and the state of the electrical equipment. The specific steps include:
[0060] S11. Establish a potential result database for instructions to determine the different potential results that each instruction may cause, including successful repair of the device, partial repair, repair failure, or further damage to the device. Each potential result has a different value for the device and the device holder. Therefore, the potential result probability sequence and the potential result value quantification sequence can be set according to actual needs to obtain the initial instruction expectation; the potential result probability sequence includes the probabilities assigned by the system to the potential results caused by all instructions, the first The potential outcome probability sequence of an instruction is expressed as , represents the potential probability of successful repair, represents the potential probability of partial repair, represents the potential probability of repair failure, Represents the potential probability of further damage; the potential result value quantization sequence is expressed as , Indicates The quantitative value of a successful equipment repair, Indicates The quantified value of the partial repair of a piece of equipment, Indicates The quantitative value of a failed device repair, Indicates The quantitative value of further damage to the equipment; let the instruction issued by the supervisor be The device operated by the operator is the device, by The potential result probability sequence of each device is matched with the potential result value quantification sequence, and then multiplied and summed item by item to calculate the guidance personnel at this time. The initial instruction expectation of a device is calculated as follows: .
[0061] S12, calculating the danger value of the electrical equipment by the temperature and vibration amplitude of the electrical equipment; the danger value of the electrical equipment is calculated by Equipment evenly installed A temperature sensor and collects time Inner The vibration amplitude data set and vibration velocity data set of the electrical equipment with the time interval are obtained. The electrical equipment hazard value of each device is obtained by weighted summing the average temperature of the device, the average vibration amplitude of the device, and the average vibration speed of the device. The calculation formula is: , Indicates The average temperature of each device, Indicates Device time The average vibration amplitude of the internal equipment, Indicates Device time The average vibration velocity of the internal equipment, represents the temperature mean weight, represents the mean weight of the vibration amplitude, Represents the mean weight of vibration velocity.
[0062] S13. Setting the danger threshold of electrical equipment , combined with the real-time danger value of the electrical equipment, dynamically adjust the initial instruction expectation to update the initial instruction expectation, obtain the instruction expectation value that is more in line with the current equipment status, calculate the ratio of the electrical equipment danger value to the electrical equipment danger threshold as the risk coefficient of equipment repair failure and further equipment damage, and use the difference between 1 and the risk coefficient of equipment repair failure as the success coefficient of equipment repair success to obtain the expected value of the instruction. The calculation formula is: ;
[0063] S2. Setting an instruction expectation threshold value. When the instruction expectation value is greater than or equal to the instruction expectation threshold value, the operator performs the operation according to the instruction issued by the instructor. When the instruction expectation value is less than the instruction expectation threshold value, the initial instruction expectation values of all instructions in the instruction database are calculated, and the maximum value is extracted as a new instruction to be transmitted to the operator.
[0064] S3. When the operator performs an operation instruction, the adaptation data of the operator under the instruction is monitored by the vital sign monitoring bracelet to obtain the personal ability value of the operator; the specific calculation steps of the personal ability value include:
[0065] S31, recording the time when the operator starts the operation through the vital signs monitoring bracelet Until the end of the operation Every time Heart rate data set collected in and blood pressure dataset ,in Indicates Heart rate data, Indicates Blood pressure data, the smaller the variance, the smaller the fluctuation of the data, so the heart rate stability is obtained by the variance of the heart rate data , the blood pressure change rate is monitored by calculating the mean of the difference between two adjacent blood pressure data. The calculation formula for the blood pressure change rate is: ,in, Indicates the average value of the heart rate data set, so as to timely discover the physiological changes of the operator during the operation;
[0066] S32. Record the time when the instruction was issued , get the operator's reaction time ;
[0067] S33, when the operation is finished, calculate the The electrical equipment hazard value of each device is used to obtain the second electrical equipment hazard value , the quality of task completion is monitored by the ratio of the difference between the two dangerous values of the electrical equipment and the sum of the two dangerous values of the electrical equipment. The quality calculation formula for task completion is: ; Comparing the difference with the ratio of the sum can eliminate the influence of the initial state of the equipment on the evaluation results and more objectively reflect the changing trend of the equipment state and the effect of maintenance;
[0068] S34, obtain the data obtained in steps S31-S32, and perform weighted summation on the above data to calculate the personal ability value of the operator:
[0069] ;
[0070] in, represents the weight of heart rate stability, represents the blood pressure change rate weight, represents the reaction time weight, It represents the weight of task completion quality. Heart rate stability and blood pressure change rate demonstrate the operator's psychological quality and can reflect the operator's physiological stability and stress coping ability during the operation to a certain extent. The vital signs monitoring bracelet records the operator's heart rate and blood pressure data, reaction time and task completion quality in real time, which can directly reflect the effect of the operator's task completion. Therefore, by weighted fusion of the above data, the operator's personal ability value can be indirectly reflected.
[0071] S4. Since the genetic algorithm can search in the entire solution space instead of being limited to a local area, an intelligent task scheduling genetic algorithm is created in combination with the task situation to adjust the task allocation according to the personal ability values, workload and current task progress of all operators; Figure 3 The specific steps of the intelligent task scheduling genetic algorithm of this embodiment are shown, including:
[0072] S41, for tasks to be assigned and Operators perform coding, using dimensional array represents the task assignment, where each value is in One of them is coded as , to for Any value in , such as , indicating that the first task is assigned to the third operator;
[0073] S42. Randomly generate a population containing multiple task allocation schemes ,Each solution is an encoded task representation;
[0074] S43. Constructing fitness function The fitness function comprehensively considers the operator's personal ability, current workload and task progress, and can intelligently adjust task allocation to ensure that tasks are assigned to the most suitable operators. Represents the weight of personal ability value, represents the task load weight, Indicates the task progress weight, Indicates the task load of the operator, which is obtained by recording the number of tasks remaining to be completed by the operator as the task load of the operator. Indicates the task progress of the operator, calculated by obtaining the standard completion time of the task , and get the current time in real time , get the task progress of the operator ;
[0075] S44, Select The task allocation scheme of the top 6 in fitness is used as the first population ;
[0076] S45, Random Selection The two task allocation schemes in are used as parent task allocation schemes, and a position is selected in the parent task allocation scheme for crossover operation to form a new child task allocation scheme;
[0077] S46. In genetic algorithms, good genes can be easily destroyed due to crossover and mutation. At the same time, genetic algorithms can easily fall into premature maturity. The specific manifestation of premature maturity is: setting a fitness improvement threshold. When the difference between two consecutive fitness values of an individual is less than the fitness improvement threshold for three consecutive times, that is, the value of the new fitness minus the previous fitness is less than the fitness improvement threshold for three consecutive times, it is judged as premature. Therefore, it is necessary to set a mutation probability to jump out of the local optimal solution during the search process, and change the element value in the new offspring task allocation plan according to the mutation probability to form the second offspring task allocation plan. The specific manifestation is as follows:
[0078] Set the initial mutation probability and personal ability variation value. When the individual's personal ability value is greater than the personal ability variation value, it indicates that the individual has better adaptability to the task, that is, the requirements for the task allocation plan are lower and the optimal solution tolerance is higher. At this time, the individual can jump out of the local optimal solution by reducing the variation probability. The updated variation probability calculation formula is: ,in, represents an attenuation factor, , k represents the number of iterations at this time;
[0079] On the contrary, when the individual's personal ability value is less than or equal to the personal ability variation value, it means that the individual has a high requirement for the optimal allocation plan. At this time, in order to avoid the individual falling into the local optimal solution, the variation probability should be greatly increased to determine whether the individual has precocious phenomenon in the genetic process. If so, the variation probability will be increased by 50 times. If not, the initial variation probability will be returned.
[0080] The present application can more intelligently decide when to perform more frequent mutations and adaptively adjust the mutation probability according to the size of the operator's personal ability value; for individuals with higher personal ability values, the characteristics of their excellent individuals are protected while avoiding destroying them prematurely; for individuals with lower personal ability values and premature maturation, large-scale mutations are enforced to break the inherent pattern of the population, prompting the algorithm to explore new solution space, avoiding the algorithm from stagnating at a local optimal solution too early, so as to enhance the overall search range of the algorithm, thereby improving the efficiency and effectiveness of the algorithm as a whole.
[0081] S47, repeat steps S44-S46, and calculate the fitness function of the new task allocation scheme;
[0082] S48, the results of all fitness functions are included in the fitness sequence. When the standard deviation of the data in the fitness sequence is less than the set fitness fluctuation threshold, the iteration is stopped and the task allocation plan at this time is output.
[0083] The threshold and weight settings can be set by the operator.
[0084] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0085] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0086] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0087] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.
[0088] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the enlightenment of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the present invention and the claims, which are all within the protection of the present invention.
Claims
1. Industrial remote collaboration system based on the Internet of Things, Features: include: The IoT device layer is used to provide operators with vital sign monitoring bracelets and video transmission devices; The data transmission layer is used to transmit the video of the electrical equipment maintenance site to the instructor's monitoring terminal through the video transmission device, connect the electrical equipment maintenance site and the instructor, and transmit the operator's vital signs to the central server through the vital sign monitoring bracelet; A data processing layer, used for receiving and processing output data of the IoT device layer; The data storage layer is used to enter all instructions into the instruction database and store the output data in the data processing layer; The data processing layer includes an instruction decision module, an operator capability monitoring module and a task allocation module; The instruction decision module is used to determine whether to operate according to the instruction issued by the instructor and the state of the electrical equipment. If the result is no, the system will make instruction suggestions by calculating the expected values of all instructions; The operator capability monitoring module is used to monitor the operator's reaction and adaptability to the instruction through the vital sign monitoring bracelet when the operator executes the instruction, and output it to the task allocation module; the task allocation module is used to create an intelligent task scheduling genetic algorithm to adjust the task allocation according to the operator's reaction and adaptability to the instruction, workload and current task progress; Also includes: S1. The instructor issues an instruction based on the video data of the electrical equipment maintenance site, and the expected value of the instruction is calculated according to the instruction issued by the instructor and the state of the electrical equipment; S2. Setting an instruction expectation threshold value. When the instruction expectation value is greater than or equal to the instruction expectation threshold value, the operator performs the operation according to the instruction issued by the instructor. When the instruction expectation value is less than the instruction expectation threshold value, the initial instruction expectation values of all instructions in the instruction database are calculated, and the maximum value is extracted as a new instruction to be transmitted to the operator. S3. When the operator performs an operation instruction, the adaptation data of the operator under the instruction is monitored by the vital sign monitoring bracelet to obtain the personal ability value of the operator; S4, create an intelligent task scheduling genetic algorithm to adjust task allocation according to the individual ability values, workload and current task progress of all operators; The specific steps of S1 include: S11. Establish a potential result database of instructions, including a potential result probability sequence and a potential result value quantification sequence, to obtain initial instruction expectations; S12. Calculate the hazard value of electrical equipment by the temperature and vibration amplitude frequency of the electrical equipment; S13. Setting the danger threshold of electrical equipment , to update the initial instruction expectation and obtain the expected value of the instruction; The potential outcome probability sequence includes the probabilities assigned by the system to the potential outcomes caused by all instructions, The potential outcome probability sequence of an instruction is expressed as , represents the potential probability of successful repair, represents the potential probability of partial repair, represents the potential probability of repair failure, Represents the potential probability of further damage; the potential result value quantization sequence is expressed as , Indicates The quantitative value of a successful equipment repair, Indicates The quantified value of the partial repair of a piece of equipment, Indicates The quantitative value of a failed device repair, Indicates The quantitative value of further damage to the equipment; let the instruction issued by the supervisor be The device operated by the operator is the equipment, then the instructor is in the The initial instruction expectation calculation formula for each device is: ; The electrical equipment hazard value is determined by Equipment evenly installed A temperature sensor and collects time Inner The vibration amplitude data set and vibration velocity data set of the electrical equipment with the time interval are obtained. The calculation formula for the electrical equipment hazard value of each device is: , Indicates The average temperature of each device, Indicates Device time The average vibration amplitude of the internal equipment, Indicates Device time The average vibration velocity of the internal equipment, represents the temperature mean weight, represents the mean weight of the vibration amplitude, represents the mean weight of vibration velocity; The expected value calculation formula of the instruction is: ; The specific steps of calculating the personal ability value include: S31, recording the time when the operator starts the operation through the vital signs monitoring bracelet Until the end of the operation Every time Heart rate data set collected in and blood pressure dataset ,in Indicates Heart rate data, Indicates Blood pressure data, get heart rate stability and blood pressure change rate ,in, Represents the average value of the data in the heart rate data set; S32. Record the time when the instruction was issued , get the operator's reaction time ; S33, when the operation is finished, calculate the The electrical equipment hazard value of each device is used to obtain the second electrical equipment hazard value , then the task completion quality calculation formula is ; S34. Calculate the operator's personal capability value by obtaining data through steps S31-S32: ; in, represents the weight of heart rate stability, represents the blood pressure change rate weight, represents the reaction time weight, Indicates the task completion quality weight; The specific steps of the intelligent task scheduling genetic algorithm include: S41, for To be assigned tasks and Operators perform coding, using dimensional array represents the task assignment, where each value is in between; S42. Randomly generate a population containing multiple task allocation schemes ,Each solution is an encoded task representation; S43. Constructing fitness function ,in, Represents the weight of personal ability value, represents the task load weight, Indicates the task progress weight, Indicates the task load of the operator, which is obtained by recording the number of tasks remaining to be completed by the operator as the task load of the operator. Indicates the task progress of the operator, calculated by obtaining the standard completion time of the task , and get the current time in real time , get the task progress of the operator ; S44, Select The task allocation scheme of the top 6 in fitness is used as the first population ; S45, Random Selection The two task allocation schemes in are used as parent task allocation schemes, and a position is selected in the parent task allocation scheme for crossover operation to form a new child task allocation scheme; S46, setting a mutation probability, and changing the element values in the new child-generation task allocation scheme according to the mutation probability to form a second child-generation task allocation scheme; S47, repeat steps S44-S46, and calculate the fitness function of the new task allocation scheme; S48, the results of all fitness functions are included in the fitness sequence. When the standard deviation of the data in the fitness sequence is less than the set fitness fluctuation threshold, the iteration is stopped and the task allocation plan at this time is output.
2. According to the industrial remote collaboration system based on the Internet of Things according to claim 1, Features: The instruction decision module includes an instruction potential result database establishment unit, an instruction expectation calculation unit, an electrical equipment status monitoring unit, an instruction expectation updating unit and an instruction judgment unit; the instruction potential result database establishment unit is used to assign potential probabilities to potential results caused by all instructions in the electrical equipment maintenance process, and the potential results include successful equipment repair, partial repair, repair failure and further damage; the instruction expectation calculation unit is used to quantify the potential result value and then calculate the initial instruction expectation of the instruction issued by the instructor; the electrical equipment status monitoring unit is used to calculate the electrical equipment danger value according to the current state of the electrical equipment; the instruction expectation updating unit is used to use the electrical equipment danger value as a weight factor to adjust the initial instruction expectation.
3. According to the industrial remote collaboration system based on the Internet of Things according to claim 2, Features: The operator capability monitoring module includes a vital signs monitoring unit and an evaluation model building unit. The vital signs monitoring unit is used to obtain the operator's current adaptation data, and the adaptation data includes heart rate stability, blood pressure change rate, reaction time and task completion quality; the evaluation model building unit is used to calculate the operator's reaction and adaptability to the instruction through the operator's adaptation data.
4. According to claim 3, the industrial remote collaboration system based on the Internet of Things, Features: The mutation probability is determined by the initial mutation probability , individual ability variation value and fitness improvement threshold are obtained; When the individual's personal ability value is greater than the personal ability variation value, the variation probability is updated, and the calculation formula is: ,in represents an attenuation factor, , k represents the number of iterations at this time; when the individual's personal ability value is less than or equal to the personal ability variation value, it is judged whether the fitness of the individual in the genetic process is less than the fitness improvement threshold for three consecutive times. If it is judged as yes, the variation probability is increased by 50 times, if it is judged as no, the initial variation probability is returned.
