A smart factory production online monitoring system based on big data

Abstract

The present invention discloses an online monitoring system for smart factory production based on big data, which belongs to the technical field of smart factory production. By combining different production dangerous actions and corresponding durations of different selected equipment in the early stage with the start operation time of the selected equipment, different subsequent dangerous time periods of the selected equipment can be periodically obtained, so that the real-time production safety of the selected equipment can be supervised and analyzed in a targeted manner during the dangerous time period. The real-time production process of different production equipment with potential safety hazards screened in the early stage is targetedly monitored and analyzed, and the dangerous states of different selected equipment in different dangerous time periods are supervised and evaluated. The present invention is used to solve the technical problem that the existing solution cannot implement targeted monitoring, analysis and management of different dangerous production time periods of different production equipment, resulting in poor initiative and flexibility in factory production monitoring and management.

Description

Technical Field

[0001] The present invention relates to the field of smart factory production technology, and in particular to a smart factory production online monitoring system based on big data. Background Art

[0002] A smart factory is a factory that uses advanced information technology, automation equipment and data analysis technology to achieve intelligent, efficient and flexible production processes. Through digital technology and the Internet of Things, various links in traditional factories such as production equipment, warehouse management, and supply chain collaboration are connected and optimized to achieve higher levels of production efficiency, product quality and resource utilization.

[0003] When implementing existing factory production online monitoring solutions, most of them still remain at the stage of implementing general monitoring statistics and data analysis on production equipment and production links, and are unable to implement targeted monitoring, analysis and management of different dangerous production periods of different production equipment, resulting in poor initiative and flexibility in factory production monitoring and management. Summary of the invention

[0004] The purpose of the present invention is to provide an online monitoring system for smart factory production based on big data, which is used to solve the technical problem that the existing solutions cannot implement targeted monitoring, analysis and management of different dangerous production periods of different production equipment, resulting in poor initiative and flexibility in factory production monitoring and management.

[0005] The purpose of the present invention can be achieved through the following technical solutions:

[0006] A smart factory production online monitoring system based on big data, including a factory production target preprocessing module, which is used to preprocess and divide data for different equipment and different production processes in the factory, obtain monitoring preprocessing data and upload it to the production supervision platform;

[0007] The factory production target monitoring and analysis module is used to implement modular real-time production risk monitoring and evaluation of different equipment and different production processes in the factory according to the monitoring pre-processing data, obtain the monitoring evaluation data set, and issue real-time dynamic alarm prompts and upload them to the production supervision platform in real time; including:

[0008] Implement modular real-time production risk monitoring for the production of different production equipment during factory production, obtain the start time of different selected equipment and generate supervision instructions, obtain the action duration corresponding to all production actions that need to be completed by the selected equipment during the generation process according to the supervision instructions, and obtain all production dangerous actions and corresponding durations based on the previous screening;

[0009] The corresponding dangerous time period is obtained according to the start time of the selected equipment and the duration of different dangerous production actions, and the values ​​of all dangerous time periods corresponding to the selected equipment are extracted and sorted and combined in time order to obtain the dangerous time period array corresponding to the selected equipment;

[0010] The dangerous period arrays corresponding to all selected devices constitute a dangerous period array set;

[0011] The dangerous status of different selected equipment in different dangerous periods is supervised and evaluated. When the selected equipment enters the dangerous period to perform dangerous production actions, the movement of personnel in the production supervision area and the safety fence area set for the selected equipment is supervised by a camera device, and the monitoring and evaluation data of the selected equipment consisting of the first safety label, the second safety label, the first danger label and the danger traceability evaluation data or the second danger label are obtained; the monitoring and evaluation data corresponding to all selected equipment constitute a monitoring and evaluation data set.

[0012] Preferably, all production equipment and all production processes of the factory are obtained, and all production equipment are numbered and marked in sequence according to the order of the production process; and further, different production actions of different production equipment are numbered and marked;

[0013] When implementing safety preprocessing on all production equipment, all production equipment with safety hazards are marked as selected equipment and associated with risk tags. Corresponding production supervision areas and safety fence areas are set for the selected equipment according to the risk tags, and other production equipment are marked as normal equipment and associated with normal tags; among which, the safety fence area is enclosed in the production supervision area.

[0014] Preferably, when preprocessing the safety impact of all selected devices, the total number of all production actions corresponding to different selected devices, the total number of all production dangerous actions corresponding to different selected devices, and the duration corresponding to different production dangerous actions are counted in sequence;

[0015] All production equipment marked with numbers, different production actions of different production equipment and the associated risk labels or normal labels, the total number of all production actions corresponding to all selected equipment and the total number of all production dangerous actions, as well as the duration corresponding to different production dangerous actions constitute the monitoring preprocessing data.

[0016] Preferably, if there is no person in the production supervision area, a first safety tag is generated; if there is a stationary person in the production supervision area and outside the safety fence area, a second safety tag is generated;

[0017] If there is a moving person in the production supervision area and outside the safety fence area, a first hazard tag is generated, and a retrospective assessment is performed on the dangerous behavior of the person based on the first hazard tag to obtain hazard retrospective assessment data;

[0018] If there are people in the safety fence area, a second danger tag is generated and an alarm is issued. At the same time, the total time the person stays in the safety fence area is counted and marked as the dangerous stay time.

[0019] Preferably, the step of obtaining risk retrospective assessment data includes:

[0020] Monitor the direction of movement of personnel. If the direction of movement of personnel is the safety fence area, generate a danger implementation label and implement an alarm prompt. At the same time, count the total time that the personnel moves towards the safety fence area and mark it as the dangerous movement time.

[0021] If the person's movement is in a non-safe fence area, a dangerous stationary label is generated;

[0022] The hazard implementation label and the hazard movement duration or hazard stationary label constitute the hazard assessment data.

[0023] Preferably, the factory production safety assessment and control module is used to calculate the safety risks of different production equipment and different production links in the factory according to the monitoring and assessment data set to obtain the corresponding operational hazard level, and implement targeted alarm prompts and control on the operation of different production equipment according to the operational hazard level.

[0024] Preferably, the monitoring and evaluation data corresponding to all selected devices in the monitoring and evaluation data set are obtained and traversed, and the safety risk implementation data of the abnormal production operation occurring in the corresponding selected device is calculated according to the hazard implementation label and the second hazard label obtained through the traversal;

[0025] According to the hazard implementation label and the second hazard label, the device weight Qz of the selected device is obtained, and the hazard movement time Ty and hazard stay time Tt of the selected device are obtained. The safety risk integration formula γ=∑ 1 M Qz×(μ1×Ty+μ2×Tt) is used to calculate the operation risk γ of the corresponding production batch of the factory production; where μ1 and μ2 are different risk impact factors, 0<μ1<μ2<1; M is the total number of occurrences of the risk implementation label and the second risk label;

[0026] The overall safety risk of all selected equipment during operation is evaluated and classified according to the degree of operational hazard.

[0027] Preferably, the overall safety risk of all selected devices during operation is evaluated and classified according to the operation risk. When the operation risk is not greater than the operation risk threshold corresponding to the selected device, a light operation risk label is generated; when the operation risk is greater than the operation risk threshold corresponding to the selected device, a heavy operation risk label is generated.

[0028] The operation light hazard label or the operation severe hazard label constitutes the safety risk analysis data for the corresponding production batch of the factory production; when implementing targeted alarm prompts and control on the operation of different production equipment based on the safety risk analysis data, the safety risk analysis data is traversed, and pre-job training management of the corresponding degree of danger is implemented for subsequent factory production based on the operation light hazard label or operation severe hazard label obtained through the traversal.

[0029] Compared with the existing solutions, the present invention achieves the following beneficial effects:

[0030] The present invention implements all-round data monitoring, statistics and classification processing on the whole process of factory production and different production equipment, so as to provide reliable data support for the subsequent safety supervision and processing management of different production equipment and production processes; through the different production dangerous actions and corresponding durations of different selected equipment in the early stage combined with the start operation time of the selected equipment, the different subsequent dangerous time periods of the selected equipment can be periodically obtained, so that the real-time production safety of the selected equipment can be supervised and analyzed in a targeted manner during the dangerous period, thereby improving the preprocessing effect of key monitoring implementation of different selected equipment.

[0031] The present invention conducts targeted monitoring and analysis on the real-time production processes of different production equipment with safety hazards screened in advance, and supervises and evaluates the dangerous status of different selected equipment in different dangerous periods, so as to timely and efficiently provide targeted alarm prompts and management for the production status of different selected equipment locally, thereby improving the initiative and predictability of the dangerous monitoring and analysis of production equipment, and at the same time can provide reliable local data support for the overall operational dangerous status analysis of subsequent factory production, thereby improving the diversity and flexibility of factory production monitoring data analysis and utilization.

[0032] The present invention integrates and calculates different production operation hazard states of different equipment in factory production to obtain the overall operation hazard level of factory production, and evaluates and classifies the overall operation hazard situation of factory production according to the operation hazard level to obtain safety risk analysis data, and provides targeted prompts and management for different production equipment and different production processes of subsequent factory production based on the safety risk analysis data, thereby improving the flexibility and initiative of factory production monitoring and operation management. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The present invention will be further described below in conjunction with the accompanying drawings.

[0034] Figure 1 This is a module block diagram of a smart factory production online monitoring system based on big data in the present invention. DETAILED DESCRIPTION

[0035] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary operation and maintenance personnel in this field without creative work are within the scope of protection of the present invention.

[0036] Example 1: Figure 1 As shown, the present invention is a smart factory production online monitoring system based on big data, including a factory production target preprocessing module and a factory production target monitoring and analysis module;

[0037] The factory production target preprocessing module is used to preprocess and divide the data of different equipment and different production processes in the factory, obtain the monitoring preprocessing data and upload it to the production supervision platform; including:

[0038] Obtain all production equipment and all production processes produced by the factory, number all production equipment in sequence according to the order of the production process and mark them as i, i = 1, 2, 3, ..., n; n is a positive integer; and further number different production actions of different production equipment and mark them as ij, j = 1, 2, 3, ..., m; m is a positive integer;

[0039] It should be noted that the application scenario in the embodiment of the present invention may be factory production involving personnel safety operations, such as steel factory production, where different production equipment has at least one production action, and different production actions correspond to different safety hazards. The safety hazards may be determined based on the work experience of those skilled in the art, or based on the big data of historical production accidents produced by the factory;

[0040] When implementing safety preprocessing for all production equipment, all production equipment with potential safety hazards are marked as selected equipment and associated with risk tags. Corresponding production supervision areas and safety fence areas are set for the selected equipment according to the risk tags, and other production equipment are marked as normal equipment and associated with normal tags; the safety fence area is enclosed in the production supervision area;

[0041] Specifically, the length and width of the selected device are obtained, and the length and width of the selected device are respectively expanded according to the preset first expansion length and the first expansion width, and the area formed after the expansion is a safety fence area, and the length and width of the selected device are respectively expanded according to the preset second expansion length and the second expansion width, and the area formed after the expansion is a production supervision area, the first expansion length is less than the second expansion length, the first expansion width is less than the second expansion width, and the production supervision area is within the monitoring range of the monitoring device corresponding to the selected device; the specific values ​​of the first expansion length and the first expansion width, the second expansion length and the second expansion width can be customized according to the specific application scenario and the specific selected device model;

[0042] Also, when preprocessing the safety impact of all selected equipment, the total number of all production actions corresponding to different selected equipment and the total number of all production dangerous actions corresponding to different selected equipment are counted in turn. The production dangerous actions are determined based on whether the actions will cause personal safety hazards to personnel, and the duration of different production dangerous actions, and the unit of the duration is seconds;

[0043] All production equipment marked with numbers, different production actions of different production equipment and associated risk labels or normal labels, the total number of all production actions corresponding to all selected equipment and the total number of all production dangerous actions, and the duration corresponding to different production dangerous actions constitute monitoring preprocessing data;

[0044] In the embodiment of the present invention, by implementing all-round data monitoring, statistics and classification processing on the entire process of factory production and different production equipment, reliable data support can be provided for the subsequent safety supervision and processing management of different production equipment and production processes.

[0045] The factory production target monitoring and analysis module is used to implement modular real-time production risk monitoring and evaluation of different equipment and different production processes in the factory according to the monitoring pre-processing data, obtain the monitoring evaluation data set, and issue real-time dynamic alarm prompts and upload them to the production supervision platform in real time; including:

[0046] Implement modular real-time production risk monitoring for different production equipment during factory production, obtain the start time of different selected equipment and generate supervision instructions. The unit of start time is accurate to seconds. According to the supervision instructions, obtain the action duration corresponding to all production actions that need to be completed by the selected equipment during the generation process. The unit of action duration is accurate to seconds, and all production dangerous actions screened in the early stage and the corresponding duration are obtained;

[0047] The corresponding dangerous time period is obtained according to the start time of the selected equipment and the duration of different dangerous production actions, and the values ​​of all dangerous time periods corresponding to the selected equipment are extracted and sorted and combined in time order to obtain the dangerous time period array corresponding to the selected equipment;

[0048] The dangerous period arrays corresponding to all selected devices constitute a dangerous period array set;

[0049] In the embodiment of the present invention, by combining different production dangerous actions and corresponding durations of different selected equipment in the early stage with the start operation time of the selected equipment, different subsequent dangerous time periods of the selected equipment can be periodically obtained, so that the real-time production safety of the selected equipment can be supervised and analyzed in a targeted manner during the dangerous period, thereby improving the preprocessing effect of key monitoring implementation of different selected equipment.

[0050] The dangerous status of different selected equipment in different dangerous periods is supervised and evaluated. When the selected equipment enters the dangerous period and performs dangerous production actions, the movement of personnel in the production supervision area and the safety fence area set for the selected equipment is supervised by a camera device; the camera device can be an existing surveillance camera;

[0051] If there are no personnel in the production supervision area, a first safety tag is generated;

[0052] If there are stationary persons in the production supervision area and outside the safety fence area, a second safety tag is generated;

[0053] If there are moving personnel in the production supervision area and outside the safety fence area, a first hazard tag is generated, and a retrospective assessment of the dangerous behavior of the personnel is performed based on the first hazard tag to obtain hazard retrospective assessment data; including:

[0054] Monitor the direction of movement of personnel. If the direction of movement of personnel is the safety fence area, generate a danger implementation label and implement an alarm prompt. At the same time, count the total time that the personnel moves towards the safety fence area and mark it as the dangerous movement time.

[0055] If the person's movement is in a non-safe fence area, a dangerous stationary label is generated;

[0056] It should be noted that monitoring and analyzing the movement direction of personnel by means of a camera device is an existing conventional technical means, and the specific steps are not described in detail here;

[0057] The hazard implementation label and the hazard moving duration or hazard stationary label constitute the hazard assessment data;

[0058] If there is a person in the safety fence area, a second danger tag is generated and an alarm is issued. At the same time, the total time the person stays in the safety fence area is counted and marked as the dangerous stay time;

[0059] The first safety label, the second safety label, the first hazard label and the hazard traceability assessment data or the second hazard label corresponding to the selected device constitute the monitoring and assessment data; the monitoring and assessment data corresponding to all the selected devices constitute the monitoring and assessment data set;

[0060] In the embodiment of the present invention, targeted monitoring and analysis is performed on the real-time production processes of different production equipment with safety hazards that have been screened in advance, and the dangerous states of different selected equipment in different dangerous periods are supervised and evaluated, so that targeted alarm prompts and management can be made for the production states of different selected equipment in a local area in a timely and efficient manner, thereby improving the initiative and predictability of the dangerous monitoring and analysis of the production equipment, and at the same time providing reliable local data support for the subsequent overall operational dangerous state analysis of the factory production, thereby improving the diversity and flexibility of the factory production monitoring data analysis and utilization.

[0061] Embodiment 2: Based on the technical solution of Embodiment 1, a factory production safety assessment control module is further included, which is used to calculate the safety risks of different production equipment and different production links in the factory according to the monitoring and assessment data set to obtain the corresponding operation risk, and implement targeted warning prompts and control on the operation of different production equipment according to the operation risk; including:

[0062] Obtain and traverse the monitoring and evaluation data corresponding to all selected devices in the monitoring and evaluation data set, and calculate the safety risk implementation data of abnormal production operations occurring in the corresponding selected devices according to the hazard implementation label and the second hazard label obtained through the traversal;

[0063] According to the hazard implementation label and the second hazard label, the equipment weight Qz of the corresponding selected equipment can be obtained by traversing and matching the equipment name of the selected equipment with the equipment weight table pre-stored in the database. The equipment weight table consists of different equipment names and corresponding equipment weights. Different equipment names are pre-set with a corresponding equipment weight. Different equipment weights can be determined according to the total number of all production hazard actions of the corresponding equipment;

[0064] Get the dangerous movement time Ty and dangerous stay time Tt of the selected equipment, and use the safety risk integration formula γ=∑ 1 M Qz×(μ1×Ty+μ2×Tt) is used to calculate the operation risk γ of the corresponding production batch of the factory production; where μ1 and μ2 are different risk impact factors, 0<μ1<μ2<1; M is the total number of occurrences of the risk implementation label and the second risk label;

[0065] It should be noted that the operation risk level is a numerical value used to evaluate and classify the overall safety risk of factory production by integrating and calculating the dangerous operation data corresponding to all production equipment corresponding to the production batch of the factory production;

[0066] The overall safety risk of all selected equipment during operation is evaluated and classified according to the degree of operational risk. When the degree of operational risk is not greater than the operational risk threshold corresponding to the selected equipment, a label of mild operational risk is generated. The operational risk threshold is determined based on the big data corresponding to all historical production accidents produced by the same factory.

[0067] When the operation risk level is greater than the operation risk threshold corresponding to the selected device, a severe operation risk label is generated;

[0068] The operation light hazard label or the operation heavy hazard label constitutes the safety risk analysis data of the corresponding production batch produced by the factory;

[0069] When implementing targeted warning prompts and control over the operation of different production equipment based on the safety risk analysis data, the safety risk analysis data is traversed, and pre-job training management with corresponding degrees of danger is implemented for subsequent factory production based on the operation light hazard labels or operation heavy hazard labels obtained through the traversal.

[0070] In the embodiment of the present invention, unlike the prior art solutions, the production status of different production equipment in the early stage cannot be used to integrate and evaluate the overall production operation status of the factory production, which leads to the inability to adaptively provide targeted prompts and management for different production equipment and different production processes of subsequent factory production according to the overall production operation status in the early stage, and rectification training can only be implemented immediately through fixed training cycles or after an accident, resulting in poor flexibility and initiative in factory production monitoring and operation management; in the embodiment of the present invention, the different production operation hazard status of different equipment in the factory production is integrated and calculated to obtain the overall operation hazard degree of the factory production, and the overall operation hazard situation of the factory production is evaluated and classified according to the operation hazard degree to obtain safety risk analysis data, and the different production equipment and different production processes of the subsequent factory production are targetedly prompted and managed according to the safety risk analysis data, thereby improving the flexibility and initiative of factory production monitoring and operation management.

[0071] In addition, the formulas involved in the above are all dimensionless and numerical calculations. They are a formula that is closest to the actual situation obtained by collecting a large amount of data and simulating it with simulation software.

[0072] In the several embodiments provided by the present invention, it should be understood that the disclosed system can be implemented in other ways. For example, the above-described embodiments of the invention are only illustrative, for example, the division of modules is only a logical function division, and there may be other division methods in actual implementation.

[0073] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, and may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0074] In addition, each functional module in each embodiment of the present invention may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0075] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the basic features of the present invention.

[0076] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, ordinary operation and maintenance personnel in the field should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A smart factory production online monitoring system based on big data, characterized in that: It includes a factory production target preprocessing module, which is used to preprocess and divide data for different equipment and different production processes in the factory, obtain monitoring preprocessing data and upload it to the production supervision platform; The factory production target monitoring and analysis module is used to implement modular real-time production risk monitoring and evaluation of different equipment and different production processes in the factory according to the monitoring pre-processing data, obtain the monitoring evaluation data set, and issue real-time dynamic alarm prompts and upload them to the production supervision platform in real time; including: Implement modular real-time production risk monitoring for the production of different production equipment during factory production, obtain the start time of different selected equipment and generate supervision instructions, obtain the action duration corresponding to all production actions that need to be completed by the selected equipment during the generation process according to the supervision instructions, and obtain all production dangerous actions and corresponding durations based on the previous screening; The corresponding dangerous time period is obtained according to the start time of the selected equipment and the duration of different dangerous production actions, and the values ​​of all dangerous time periods corresponding to the selected equipment are extracted and sorted and combined in time order to obtain the dangerous time period array corresponding to the selected equipment; The dangerous period arrays corresponding to all selected devices constitute a dangerous period array set; The dangerous status of different selected equipment in different dangerous periods is supervised and evaluated. When the selected equipment enters the dangerous period to perform dangerous production actions, the movement of personnel in the production supervision area and the safety fence area set for the selected equipment is supervised by a camera device to obtain the monitoring and evaluation data of the selected equipment consisting of the first safety label, the second safety label, the first danger label and the danger traceability evaluation data or the second danger label; the monitoring and evaluation data corresponding to all selected equipment constitute the monitoring and evaluation data set; The factory production safety assessment and control module is used to calculate the safety risks of different production equipment and different production links in the factory according to the monitoring and assessment data set to obtain the corresponding operation risk, and implement targeted warning prompts and control on the operation of different production equipment according to the operation risk; including: Obtain and traverse the monitoring and evaluation data corresponding to all selected devices in the monitoring and evaluation data set, and calculate the safety risk implementation data of abnormal production operations occurring in the corresponding selected devices according to the hazard implementation label and the second hazard label obtained through the traversal; According to the hazard implementation label and the second hazard label, the device weight Qz of the selected device is obtained, and the hazard movement time Ty and hazard stay time Tt of the selected device are obtained. The safety risk integration formula γ=∑1 M Qz×(μ1×Ty+μ2×Tt) is used to calculate the operation risk γ of the corresponding production batch of the factory production; where μ1 and μ2 are different risk impact factors, 0<μ1<μ2<1; M is the total number of occurrences of the risk implementation label and the second risk label; The overall safety risk of all selected devices during operation is evaluated and classified according to the operation risk. When the operation risk is not greater than the operation risk threshold corresponding to the selected device, a light operation risk label is generated; when the operation risk is greater than the operation risk threshold corresponding to the selected device, a heavy operation risk label is generated. The operation light hazard label or the operation severe hazard label constitutes the safety risk analysis data for the corresponding production batch of the factory production; when implementing targeted alarm prompts and control on the operation of different production equipment based on the safety risk analysis data, the safety risk analysis data is traversed, and pre-job training management of the corresponding degree of danger is implemented for subsequent factory production based on the operation light hazard label or operation severe hazard label obtained through the traversal.

2. According to the big data-based smart factory production online monitoring system of claim 1, it is characterized in that: Obtain all production equipment and all production processes produced by the factory, number and mark all production equipment in sequence according to the order of the production process; and further number and mark different production actions of different production equipment; When implementing safety preprocessing on all production equipment, all production equipment with safety hazards are marked as selected equipment and associated with risk tags. Corresponding production supervision areas and safety fence areas are set for the selected equipment according to the risk tags, and other production equipment are marked as normal equipment and associated with normal tags; among which, the safety fence area is enclosed in the production supervision area.

3. According to the big data-based smart factory production online monitoring system of claim 2, it is characterized in that: When preprocessing the safety impact of all selected equipment, the total number of all production actions corresponding to different selected equipment, the total number of all production dangerous actions corresponding to different selected equipment, and the duration of different production dangerous actions are counted in turn; All production equipment marked with numbers, different production actions of different production equipment and the associated risk labels or normal labels, the total number of all production actions corresponding to all selected equipment and the total number of all production dangerous actions, as well as the duration corresponding to different production dangerous actions constitute the monitoring preprocessing data.

4. According to the big data-based smart factory production online monitoring system of claim 1, it is characterized in that: If there is no person in the production supervision area, a first safety tag is generated; if there is a stationary person in the production supervision area and outside the safety fence area, a second safety tag is generated; If there is a moving person in the production supervision area and outside the safety fence area, a first hazard tag is generated, and a retrospective assessment is performed on the dangerous behavior of the person based on the first hazard tag to obtain hazard retrospective assessment data; If there are people in the safety fence area, a second danger tag is generated and an alarm is issued. At the same time, the total time the person stays in the safety fence area is counted and marked as the dangerous stay time.

5. According to the big data-based smart factory production online monitoring system of claim 4, it is characterized in that: The steps to obtain hazard retrospective assessment data include: Monitor the direction of movement of personnel. If the direction of movement of personnel is the safety fence area, generate a danger implementation label and implement an alarm prompt. At the same time, count the total time that the personnel moves towards the safety fence area and mark it as the dangerous movement time. If the person's movement is in a non-safe fence area, a dangerous stationary label is generated; The hazard implementation label and the hazard movement duration or hazard stationary label constitute the hazard assessment data.

Images