Workshop cooperation abnormity early warning system based on multi-source environment parameter dynamic association

Abstract

The invention discloses a workshop collaborative abnormity early warning system based on multi-source environmental parameter dynamic association, and relates to the field of workshop safety management, and the system comprises a collection module which is used for collecting workshop environmental parameters and storing the workshop environmental parameters; the visualization module is used for receiving the workshop environment parameters acquired by the acquisition module, and generating change trend graphs representing various types of workshop environment parameters based on the workshop environment parameters; according to the invention, through dynamic acquisition and correlation analysis of multiple types of environmental parameters, subtle changes of workshop environment and equipment operation can be captured in real time, limitation of traditional single parameter monitoring is broken through, comprehensiveness and accuracy of abnormity identification are improved, and through an operation frequency dynamic adjustment mechanism, a real-time monitoring result is obtained. The data acquisition density can be intelligently optimized according to the difference of the equipment vibration signals, and accurate acquisition of key information under complex working conditions is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of workshop safety management, and specifically to a workshop collaborative anomaly warning system based on dynamic association of multi-source environmental parameters. Background Art

[0002] Workshop management is the systematic control of various elements at the production site, covering personnel, equipment, materials, processes, environment, etc. By formulating standardized processes, optimizing production capacity allocation, monitoring progress and costs, production efficiency and orderliness are ensured.

[0003] The invention patent application with the application number 202310024270.5 discloses a workshop production safety warning system, including: a plurality of monitoring terminals and a monitoring platform, and each of the monitoring terminals is wirelessly communicated with the monitoring platform; the monitoring terminal is used to obtain real-time time-domain data corresponding to each safety index related to the workshop production safety status in different regions and real-time image data of different regions; the monitoring platform is used to form a training set with the time-domain data corresponding to each safety index related to the workshop production safety status when a safety accident occurs in different regions and the original image data when a safety accident occurs in different regions: for constructing a safety warning model: and for inputting the real-time time-domain data and real-time image data into the safety warning model trained by the training set to obtain safety warning information; wherein, the safety warning model includes: a feature extraction module, a regional data correction module, a regional fusion module, a target segmentation module and an alarm module; the feature extraction module is used to extract smoke feature data from the real-time image data of different regions, and at the same time extract index feature data from the real-time time-domain data corresponding to each safety index in different regions; the regional data correction module is used to correct and compensate the smoke feature data according to a plurality of index feature data to obtain complete regional smoke feature data; the regional fusion module is used to restore the regional smoke feature data to the original image data and splice and fuse the image data of each region; the target segmentation module is used to segment the complete global smoke target image data from the spliced and fused image data and obtain new smoke feature data of the global smoke target image data. This application aims to solve the problem of "how to obtain accurate small smoke concentration data at the beginning of a fire without affecting the normal operation of the workshop".

[0004] However, for the workshop production scenario, the environmental information volume is huge. Most of the existing technologies monitor a single environmental information item to carry out distributed safety control for the workshop. In this way, the warning effect coverage for the workshop is not comprehensive, and the monitoring results are independent, resulting in difficulty in comprehensively evaluating workshop anomaly problems;

[0005] Therefore, a workshop collaborative anomaly warning system based on dynamic association of multi-source environmental parameters is proposed. Summary of the Invention

[0006] In view of the above disadvantages of the prior art, the present invention provides a workshop collaborative anomaly warning system based on dynamic association of multi-source environmental parameters, which can effectively solve the problems of the prior art.

[0007] To achieve the above objectives, the present invention is realized through the following technical solutions;

[0008] The present invention discloses a workshop collaborative anomaly warning system based on dynamic association of multi-source environmental parameters, including:

[0009] A collection module, used to collect workshop environmental parameters and store the workshop environmental parameters; a visualization module, used to receive the workshop environmental parameters collected by the operation of the collection module, and respectively generate graphs representing the change trends of various types of workshop environmental parameters based on the workshop environmental parameters; a diagnosis module, used to traverse the change trend graphs generated by the operation of the visualization module, configure warning thresholds for each change trend graph, and monitor each corresponding change trend graph based on the warning thresholds configured for each change trend graph. When the value represented in the change trend graph exceeds the corresponding warning threshold, it is determined that there is an operation risk in the workshop; an analysis module, used to receive the change trend graphs generated in the visualization module, and analyze the workshop operation fault tendency based on the change trend graphs; a determination module, used to receive the workshop operation fault tendency analyzed in the analysis module, set an operation fault determination threshold, and based on the comparison between the workshop operation fault tendency and the operation fault determination threshold, when the workshop operation fault tendency is greater than the operation fault determination threshold, it is determined that there is a fault in the workshop operation; a message module, used to obtain the operation result data of the diagnosis module, the analysis module, and the determination module, combine the operation result data of each module to generate a system operation message, and feedback it to the system end user.

[0010] Furthermore, the collection module is integrated by sensing devices capable of sensing the dust content, temperature, humidity, vibration signals of equipment in the workshop, and the proportion of harmful gas components in the air in the workshop. The dust content, temperature, humidity, vibration signals of equipment in the workshop, and the proportion of harmful gas components in the air are the workshop environmental parameters. When the collection module stores the workshop environmental parameters, a collection timestamp is marked for each environmental parameter, and the environmental parameters are stored separately based on the environmental parameter type;

[0011] Among them, several collection modules are provided, and the several collection modules are distributed in a matrix shape in the internal space of the workshop. The distances between the collection modules are equal, and the operating frequencies are the same and synchronous.

[0012] Furthermore, during the operation of several groups of the collection modules, the operating frequency continuously changes with reference to the vibration signals of the equipment in the workshop within a preset change range, and the change process follows:

[0013] Continuously run based on a preset initial operating frequency. After running continuously for at least two times, obtain the vibration signals of the equipment in the workshop sensed during each run. Always use the latest two sets of vibration signals of the equipment in the workshop to identify the difference in vibration signals, and control the operating frequency of the acquisition module to increase as the difference increases and decrease as the difference decreases.

[0014] Among them, when there is more than one piece of equipment in the workshop, the difference in vibration signals used to control the operating frequency of the acquisition module is the average value of the differences in vibration signals of each piece of equipment.

[0015] Furthermore, the difference in vibration signals of the equipment in the workshop is expressed as:

[0016] ;

[0017] In the formula: is the difference between vibration signal X and vibration signal Y; is the number of sampling points; are the amplitudes of signal X and signal Y at the i-th sampling point; are the amplitudes of the j-th frequency component in the spectrum of signal X and the j-th frequency component in the spectrum of signal Y; , are the phases of signal X and signal Y at the i-th sampling point;

[0018] Among them, the positive frequency part of the spectrum of signal X is denoted as , and the positive frequency part of the spectrum of signal Y is denoted as .

[0019] Furthermore, during the operation stage of the visualization module, the generated trend graphs correspond one-to-one with various types of workshop environment parameters, and the trend graphs representing various types of workshop environment parameters are line graphs, and the workshop environment parameters represented in the line graphs are updated in real time based on the newly acquired workshop environment parameters by the acquisition module.

[0020] Furthermore, when the diagnostic module does not determine that the value represented in the trend graph exceeds the corresponding warning threshold, it determines that the workshop is operating safely and synchronously refreshes the system operation;

[0021] A monitoring unit and a picking unit are set under the diagnostic module. The monitoring unit is used to monitor whether the source change trend graph of the value exceeding the corresponding warning threshold is unique when the diagnostic module determines that there are operation risks during the operation stage of the workshop;

[0022] Unique: Trigger the operation of the picking unit to pick the trend graph most similar to the source change trend graph of the value exceeding the warning threshold.

[0023] Not unique: The workshop is shut down, and the environment and equipment in the workshop are coordinated and maintained to restore the environment and equipment in the workshop to the preset state;

[0024] Among them, during the operation stage of the picking unit, the picking targets are the numerical source change trend graph exceeding the warning threshold, the change trend graph representing the vibration signal of the equipment in the workshop, and the change trend graph most similar to the numerical source change trend graph exceeding the warning threshold;

[0025] When the picking target is the numerical source change trend graph exceeding the warning threshold and the change trend graph representing the vibration signal of the equipment in the workshop are the same, there are only two groups of change trend graphs picked up by the picking unit, and the change trend graphs picked up by the picking unit during operation are synchronously forwarded to the analysis module.

[0026] Furthermore, the similarity calculation logic of the change trend graph is expressed as:

[0027] ;

[0028] In the formula: is the similarity between the change trend graph a and the change trend graph b; 、 are the total number of nodes on the multi-segment broken lines representing numerical values in the change trend graph a and the change trend graph b; is the coordination factor; is the total number of intersection nodes on the multi-segment broken lines representing numerical values in the change trend graph a and the change trend graph b starting from the origin of the change trend graph in the horizontal axis direction; 、 are the lengths of the line segments representing the q-th node to the (q + 1)-th node in the change trend graph a and the lengths of the line segments representing the q-th node to the (q + 1)-th node in the change trend graph b; 、 are the slopes of the line segments representing the q-th node to the (q + 1)-th node in the change trend graph a and the slopes of the line segments representing the q-th node to the (q + 1)-th node in the change trend graph b;

[0029] Among them, represents the operation of taking the average value of The coordination factor takes a value of 1 or -1. If the numerator of the fraction where the coordination factor is located is less than or equal to the denominator, the coordination factor takes a value of 1; otherwise, the coordination factor takes a value of -1.

[0030] Furthermore, the workshop operation fault tendency analysis logic in the analysis module is expressed as:

[0031] ;

[0032] In the formula: is the workshop operation fault tendency; The difference in parameters in the graph of the change trend of the value source exceeding the warning threshold; The difference in parameters in the change trend graph that is most similar to the change trend graph of the value source exceeding the warning threshold; Is And Excluding the change trend graph pointed to by, the total number of nodes in the change trend graph; Is And Excluding the change trend graph pointed to by, the warning threshold configured for the change trend graph; Is the representation value of the v-th node;

[0033] When there are only two groups of change trend graphs picked up by the picking unit, the third product term in the logical formula for calculating Is replaced by the constant 1. When the difference calculation target in the formula is the vibration signal of equipment not in the workshop, its difference calculation logic is expressed as:

[0034] Obtain the latest two values in the change trend graph, and record them as MAX(I) and MIN(I) based on the magnitudes of the two values. Then the difference calculation logic is expressed as ;

[0035] Among them, the fault determination thresholds set in the determination module correspond one-to-one with the environmental parameters of each workshop. When the determination module compares the fault determination threshold with the fault tendency of the workshop operation, during the operation stage of the diagnosis module, it selects the fault determination threshold corresponding to the environmental parameters of the workshop where the change trend graph of the value source exceeding the warning threshold is located to perform the comparison operation.

[0036] Furthermore, when the determination module determines that there is a fault in the workshop operation, the workshop shuts down, and the environment and equipment in the workshop are coordinated and maintained to restore the environment and equipment in the workshop to the preset state;

[0037] When the determination module determines that there is no fault in the workshop operation, it takes the management equipment of the environmental parameters of the workshop corresponding to the change trend graph of the value source exceeding the warning threshold picked up by the picking unit as the maintenance target for offline maintenance.

[0038] Furthermore, the acquisition module is interactively connected with the visualization module and the diagnosis module through a wireless network. The lower level of the diagnosis module is interactively connected with a monitoring unit and a picking unit through a wireless network. The diagnosis module is interactively connected with an analysis module and a determination module through a wireless network. The determination module is interactively connected with a message module through a wireless network.

[0039] Adopting the technical solution provided by the present invention, compared with the known prior art, it has the following beneficial effects:

[0040] The present invention provides a workshop collaborative anomaly early warning system based on dynamic association of multi-source environmental parameters. During the operation of this system, through the dynamic acquisition and correlation analysis of multi-type environmental parameters, it can capture the subtle changes in the workshop environment and equipment operation in real time, break through the limitations of traditional single-parameter monitoring, improve the comprehensiveness and accuracy of anomaly recognition. Through the dynamic adjustment mechanism of operation frequency, it can intelligently optimize the data acquisition density according to the differences in equipment vibration signals, ensure accurate acquisition of key information under complex working conditions, and with the similarity calculation and fault tendency analysis model, it can deeply explore the potential associations between parameters, predict the development trend of faults in advance, and realize the full-process intelligent management from risk early warning to fault determination. The system can not only quickly locate the source of anomalies and trigger hierarchical responses when risks occur, but also formulate targeted maintenance strategies based on the analysis results, effectively reduce unnecessary downtime, and improve the safety, stability and maintenance efficiency of workshop operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for description in the embodiments or the prior art. Obviously, the drawings described below are only some embodiments of the present invention, and those of ordinary skill in the art can obtain other drawings based on these drawings without creative efforts.

[0042] Figure 1 It is a schematic structural diagram of a workshop collaborative anomaly early warning system based on dynamic association of multi-source environmental parameters. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0043] To make the objectives, technical solutions and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the scope of protection of the present invention.

[0044] The following further describes the present invention with reference to the embodiments.

[0045] Embodiment:

[0046] The workshop collaborative anomaly early warning system based on dynamic association of multi-source environmental parameters in this embodiment, as Figure 1 shown, includes:

[0047] An acquisition module, configured to acquire workshop environmental parameters and store the workshop environmental parameters;

[0048] The acquisition module is integrated by sensing devices that can sense the dust content, temperature, humidity, vibration signals of equipment in the workshop, and the proportion of harmful gas components in the air. The dust content, temperature, humidity, vibration signals of equipment in the workshop, and the proportion of harmful gas components in the air are the workshop environmental parameters. When the acquisition module stores the workshop environmental parameters, a collection timestamp is marked for each environmental parameter, and the environmental parameters are stored separately based on the type of environmental parameter;

[0049] Among them, several acquisition modules are set up, and several acquisition modules are distributed in the internal space of the workshop in a matrix shape. The distances between the acquisition modules are equal, and the operating frequencies are the same and synchronous;

[0050] During the operation of several groups of acquisition modules, the operating frequency continuously changes with reference to the vibration signals of the equipment in the workshop within a preset change range. The change process follows:

[0051] Based on the preset initial operating frequency, it runs continuously. After running continuously for at least twice, the vibration signals of the equipment in the workshop sensed each time are obtained. The difference in vibration signals is always identified using the latest two sets of vibration signals of the equipment in the workshop, and the operating frequency of the acquisition module is controlled to increase as the difference increases and decrease as the difference decreases;

[0052] Among them, when there is more than one piece of equipment in the workshop, the difference in vibration signals used to control the operating frequency of the acquisition module is the average value of the differences in vibration signals of each piece of equipment;

[0053] The difference in vibration signals of the equipment in the workshop is expressed as:

[0054] ;

[0055] In the formula: is the difference between vibration signal X and vibration signal Y; is the number of sampling points; are the amplitudes of signal X at the i-th sampling point and the amplitude of signal Y at the i-th sampling point; are the amplitudes of the j-th frequency component in the spectrum of signal X and the amplitude of the j-th frequency component in the spectrum of signal Y; 、 are the phases of signal X at the i-th sampling point and the phase of signal Y at the i-th sampling point;

[0056] Among them, the positive frequency part of the spectrum of signal X is denoted as , and the positive frequency part of the spectrum of signal Y is denoted as ;

[0057] Through the calculation of the above logical formula, the difference in vibration signals of the equipment in the workshop is obtained for controlling the operating frequency of the acquisition module;

[0058] A visualization module, which is used to receive the workshop environment parameters collected by the acquisition module during operation, and generate trend graphs representing the change trends of various types of workshop environment parameters based on the workshop environment parameters;

[0059] During the operation stage of the visualization module, the generated trend graphs correspond one-to-one with various types of workshop environment parameters, and the trend graphs representing the change trends of various types of workshop environment parameters are line graphs, and the workshop environment parameters represented in the line graphs are updated in real time based on the newly collected workshop environment parameters by the acquisition module during operation;

[0060] A diagnosis module, which is used to traverse the trend graphs generated during the operation of the visualization module, configure warning thresholds for each trend graph, monitor each corresponding trend graph based on the configured warning thresholds for each trend graph, and determine that there is an operation risk in the workshop when the value represented in the trend graph exceeds the corresponding warning threshold;

[0061] When the diagnosis module does not determine that the value represented in the trend graph exceeds the corresponding warning threshold, it determines that the workshop is operating safely and synchronously refreshes the system operation;

[0062] A monitoring unit and a picking unit are set under the diagnosis module. The monitoring unit is used to monitor whether the source change trend graph of the value exceeding the corresponding warning threshold is unique when it is determined that there is an operation risk in the workshop during the operation stage of the diagnosis module;

[0063] Unique: Trigger the operation of the picking unit to pick the trend graph most similar to the trend graph of the value source exceeding the warning threshold;

[0064] Not unique: Shut down the workshop, coordinate and maintain the environment and equipment in the workshop to restore the environment and equipment in the workshop to the preset state;

[0065] Among them, during the operation stage of the picking unit, the picking targets are the trend graph of the value source exceeding the warning threshold, the trend graph representing the vibration signal of the equipment in the workshop, and the trend graph most similar to the trend graph of the value source exceeding the warning threshold;

[0066] When the picking target is the same as the trend graph of the value source exceeding the warning threshold and the trend graph representing the vibration signal of the equipment in the workshop, there are only two groups of trend graphs picked by the picking unit, and the trend graphs picked by the picking unit during operation are synchronously forwarded to the analysis module;

[0067] The similarity calculation logic of the trend graph is expressed as:

[0068] ;

[0069] In the formula: is the similarity between trend graph a and trend graph b; , is the total number of nodes on the multi-segment broken lines representing values in the change trend graph a and the change trend graph b; is the coordination factor; is the total number of intersection nodes on the multi-segment broken lines representing values in the change trend graph a and the change trend graph b starting from the origin of the change trend graph towards the horizontal axis direction; , are the lengths of the line segments representing the q-th node to the (q + 1)-th node in the change trend graph a and the lengths of the line segments representing the q-th node to the (q + 1)-th node in the change trend graph b; , are the slopes of the line segments representing the q-th node to the (q + 1)-th node in the change trend graph a and the slopes of the line segments representing the q-th node to the (q + 1)-th node in the change trend graph b;

[0070] Among them, represents the operation of taking the average value of The coordination factor takes a value of 1 or -1. If the numerator of the fraction where the coordination factor is located is less than or equal to the denominator, the coordination factor takes a value of 1; otherwise, the coordination factor takes a value of -1;

[0071] The similarity calculation logic between change trend graphs is limited by the above logical formula;

[0072] The analysis module is used to receive the change trend graphs generated in the visualization module and analyze the workshop operation fault tendency based on the change trend graphs;

[0073] The workshop operation fault tendency analysis logic in the analysis module is expressed as:

[0074] ;

[0075] In the formula: is the workshop operation fault tendency; is the difference in parameters in the change trend graph of the numerical source exceeding the warning threshold; is the difference in parameters in the change trend graph most similar to the change trend graph of the numerical source exceeding the warning threshold; is except for and the total number of nodes in the change trend graph other than the change trend graph pointed to; is except for and the warning threshold configured for the change trend graph other than the change trend graph pointed to; is the represented value of the v-th node;

[0076] When there are only two groups of change trend graphs picked up by the picking unit, calculate In the logical formula, the third product term is replaced by the constant 1. When the target of difference calculation is the vibration signal of equipment outside the workshop, the difference calculation logic is expressed as:

[0077] Obtain the latest two values in the change trend graph. Based on the magnitudes of the two values, denote them as MAX(I) and MIN(I). Then the difference calculation logic is expressed as ;

[0078] Through the above logical formula, analyze the fault tendency of the workshop operation to provide support for the further operation of the determination module in the system;

[0079] Among them, the fault determination thresholds set in the determination module correspond one-to-one with the environmental parameters of each workshop. When the determination module compares the fault determination threshold with the fault tendency of the workshop operation, during the operation stage of the diagnostic module, the fault determination threshold corresponding to the environmental parameter of the workshop to which the numerical source change trend graph exceeding the warning threshold belongs is selected for the comparison operation;

[0080] The determination module is used to receive the fault tendency of the workshop operation analyzed in the analysis module, set the operation fault determination threshold, and based on the comparison between the fault tendency of the workshop operation and the operation fault determination threshold, when the fault tendency of the workshop operation is greater than the operation fault determination threshold, it is determined that there is a fault in the workshop operation;

[0081] When the determination module determines that there is a fault in the workshop operation, the workshop stops operating, and the environment and equipment in the workshop are coordinated and maintained to restore the environment and equipment in the workshop to the preset state;

[0082] When the determination module determines that there is no fault in the workshop operation, the equipment corresponding to the environmental parameter of the workshop to which the numerical source change trend graph picked up by the picking unit and exceeding the warning threshold belongs is used as the maintenance target for offline maintenance;

[0083] The message module is used to obtain the operation result data of the diagnostic module, analysis module, and determination module, combine the operation result data of each module to generate a system operation message, and feedback it to the system-end user;

[0084] The acquisition module is interactively connected to the visualization module and the diagnostic module through a wireless network. The lower level of the diagnostic module is interactively connected to a monitoring unit and a picking unit through a wireless network. The diagnostic module is interactively connected to the analysis module and the determination module through a wireless network. The determination module is interactively connected to the message module through a wireless network.

[0085] In this embodiment, the acquisition module runs to acquire the workshop environmental parameters, stores the workshop environmental parameters, the visualization module synchronously receives the workshop environmental parameters acquired by the acquisition module, generates graphs representing the change trends of various types of workshop environmental parameters respectively based on the workshop environmental parameters, the diagnosis module runs later to traverse the change trend graphs generated by the visualization module, configures warning thresholds for each change trend graph, monitors each corresponding change trend graph based on the warning thresholds configured for the change trend graphs, when the value represented in the change trend graph exceeds the corresponding warning threshold, it is determined that there is an operation risk in the workshop, the monitoring unit synchronously monitors whether the source change trend graph of the value exceeding the warning threshold is unique when it is determined that there is an operation risk in the workshop during the operation stage of the diagnosis module, when the diagnosis result is yes, the pick-up unit picks up the change trend graph most similar to the source change trend graph of the value exceeding the warning threshold, then the analysis module receives the change trend graphs generated in the visualization module, analyzes the workshop operation fault tendency based on the change trend graphs, further the determination module receives the workshop operation fault tendency analyzed in the analysis module, sets an operation fault determination threshold, compares the workshop operation fault tendency with the operation fault determination threshold, when the workshop operation fault tendency is greater than the operation fault determination threshold, it is determined that there is a fault in the workshop operation, and finally the message module obtains the operation result data of the diagnosis module, the analysis module and the determination module, combines the operation result data of each module to generate a system operation message, and feeds it back to the system-end user.

[0086] Through the operation of the system in the above embodiment, a system for collaborative abnormal warning and fault diagnosis applying multiple environmental parameters is provided for the workshop to serve the daily operation safety management of the workshop.

[0087] The following gives an example application instance of the system in the above embodiment:

[0088] The xx auto parts manufacturing workshop has an area of 5000 square meters and is equipped with more than 80 production equipment of various types such as stamping, welding, and assembly. The workshop environmental parameters include dust content, temperature, humidity, equipment vibration signal, component ratio of harmful gases (such as carbon monoxide generated by welding), etc. To ensure production safety and efficiency, the "Workshop Collaborative Abnormal Warning System Based on Dynamic Association of Multi-source Environmental Parameters" is introduced. 20 acquisition modules are evenly distributed in a matrix shape in the workshop, with a module spacing of 5 meters, and the initial operation frequency is set to collect once per minute.

[0089] (I) Data Acquisition and Storage

[0090] The acquisition module continuously senses the workshop environmental parameters, adds a collection timestamp accurate to the second to each parameter, and stores them in the system database classified by types such as dust and temperature. For example, the acquisition module in the welding area collects data such as welding fume concentration and equipment vibration frequency in real time, and each type of data is stored independently for subsequent analysis.

[0091] (2) Visual Analysis

[0092] The visualization module converts various environmental parameters into a line chart that updates in real time. Taking the vibration signal of the equipment as an example, the system generates an independent line chart for each piece of equipment. The horizontal axis represents time, and the vertical axis represents parameters such as vibration amplitude and frequency. The line chart of the vibration signal of a certain stamping machine can display the vibration fluctuation during its operation in real time, facilitating the operator to directly observe the operating state of the equipment.

[0093] (3) Abnormal Diagnosis and Risk Judgment

[0094] The diagnosis module sets a warning threshold for each line chart. For example, the warning threshold for the vibration amplitude of the equipment is set at 80 dB. When the amplitude in the line chart of the vibration signal of a certain welding robot exceeds 80 dB continuously for 3 times, the diagnosis module determines that there is an operating risk. At this time, the monitoring unit checks whether the source of the value exceeding the warning threshold is unique. If only the vibration signal of this robot is abnormal, the picking unit is triggered to pick the line chart of the vibration signal of other equipment that is most similar to this line chart (such as the vibration chart of another robot of the same model) and the vibration chart of this robot, and synchronously forward them to the analysis module.

[0095] (4) Fault Trend Analysis and Disposal

[0096] The analysis module calculates the fault trend value according to the formula. Suppose the difference (DIFFOUT) of the vibration signal of this welding robot is 0.6, the difference (DIFFSIMM|MAX) of the similar line chart is 0.4, the total number of other environmental parameter nodes is 50, and the average value of the warning threshold is 0.5. Then the fault trend F = 0.6×0.4×(50×0.5) = 6. The determination module compares the F value with the fault determination threshold corresponding to this equipment (set at 5). Since 6 > 5, it is determined that there is a fault. The workshop immediately shuts down this robot and conducts a comprehensive inspection of its robotic arm, transmission components, etc., discovers a problem of gear wear and replaces it in time to restore the equipment to the preset state.

[0097] (5) Routine Maintenance and System Optimization

[0098] When the diagnosis module does not detect any abnormalities, the system automatically refreshes and runs. If in a certain detection, multiple acquisition modules simultaneously detect that the dust concentration in the workshop is close to the warning threshold (such as reaching 50 mg / m³, and the warning threshold is 60 mg / m³), but does not exceed it, the determination module sets the dust filtration equipment as the maintenance target and arranges staff to carry out offline maintenance such as filter element replacement to prevent potential abnormalities.

[0099] In addition, the operating frequency of the acquisition module is dynamically adjusted according to the device vibration signal. When the difference in vibration signals increases due to the simultaneous operation of multiple devices (such as during full-load production on a production line), the acquisition frequency is automatically increased to 1.5 times per minute to ensure timely capture of subtle abnormalities. When the number of devices in operation is small and the difference in vibration signals decreases during the off-season of production, the frequency returns to the initial value to save system resources.

[0100] In summary, during the operation of the system in the above embodiments, through the dynamic acquisition and correlation analysis of multiple types of environmental parameters, subtle changes in the workshop environment and equipment operation can be captured in real time, breaking through the limitations of traditional single-parameter monitoring, enhancing the comprehensiveness and accuracy of anomaly identification. Through the dynamic adjustment mechanism of the operating frequency, the data acquisition density can be intelligently optimized according to the difference in device vibration signals, ensuring accurate acquisition of key information under complex working conditions. Moreover, with the similarity calculation and fault tendency analysis model, potential correlations between parameters can be deeply explored, and the development trend of faults can be predicted in advance, realizing the full-process intelligent management from risk warning to fault determination. The system can not only quickly locate the source of anomalies and trigger hierarchical responses when risks occur, but also formulate targeted maintenance strategies based on the analysis results, effectively reducing unnecessary downtime and enhancing the safety, stability, and maintenance efficiency of workshop operation.

[0101] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements will not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A workshop collaborative anomaly warning system based on dynamic association of multi-source environmental parameters, characterized in that, Including: A collection module for collecting workshop environmental parameters and storing the workshop environmental parameters; A visualization module for receiving the workshop environmental parameters collected by the operation of the collection module and generating graphs representing the change trends of various types of workshop environmental parameters respectively based on the workshop environmental parameters; A diagnosis module for traversing the change trend graphs generated by the operation of the visualization module, configuring warning thresholds for each change trend graph, monitoring each corresponding change trend graph based on the warning thresholds configured for the change trend graphs, and determining that there is an operation risk in the workshop when the value represented in the change trend graph exceeds the corresponding warning threshold; An analysis module for receiving the change trend graphs generated in the visualization module and analyzing the tendency of workshop operation faults based on the change trend graphs; A determination module for receiving the tendency of workshop operation faults analyzed in the analysis module, setting an operation fault determination threshold, and determining that there is a fault in the workshop operation when the tendency of workshop operation faults is greater than the operation fault determination threshold based on the comparison between the tendency of workshop operation faults and the operation fault determination threshold; A message module for obtaining the operation result data of the diagnosis module, the analysis module and the determination module, combining the operation result data of each module to generate a system operation message, and feeding it back to the system-side user.

2. The workshop collaborative anomaly early warning system based on dynamic association of multi-source environmental parameters according to claim 1, characterized in that, The collection module is integrated by sensing devices capable of sensing the dust content, temperature, humidity, vibration signals of equipment in the workshop, and the proportion of harmful gas components in the air in the workshop. The dust content, temperature, humidity, vibration signals of equipment in the workshop, and the proportion of harmful gas components in the air are the workshop environmental parameters. When the collection module stores the workshop environmental parameters, a collection timestamp is marked for each environmental parameter, and the environmental parameters are stored separately based on the environmental parameter type; Among them, several collection modules are provided, and the several collection modules are distributed in a matrix in the internal space of the workshop. The spacing between each collection module is equal, and the operating frequencies are the same and synchronous.

3. The workshop collaborative anomaly warning system based on dynamic association of multi-source environmental parameters according to claim 2, characterized in that, During the operation of several groups of the collection modules, the operating frequency continuously changes with reference to the vibration signals of the equipment in the workshop within a preset change range, and the change process follows: Continuously operate based on the preset initial operating frequency. After continuously operating not less than twice, obtain the vibration signals of the equipment in the workshop sensed each time. Always use the latest two sets of vibration signals of the equipment in the workshop to identify the difference in vibration signals, and control the operating frequency of the collection module to increase as the difference increases and decrease as the difference decreases; Among them, when the equipment in the workshop is not unique, the difference in vibration signals used to control the operating frequency of the collection module is the average value of the differences in vibration signals of each equipment.

4. The workshop collaborative anomaly warning system based on dynamic association of multi-source environmental parameters according to claim 3, wherein The difference in vibration signals of the equipment in the workshop is expressed as: ； Wherein: is the difference between the vibration signal X and the vibration signal Y; is the number of sampling points; are the amplitudes of signal X and signal Y at the i-th sampling point; are the amplitudes of the j-th frequency component in the spectrum of signal X and the j-th frequency component in the spectrum of signal Y; and are the phases of signal X and signal Y at the i-th sampling point; Among them, the positive frequency part of the spectrum of signal X is denoted as , and the positive frequency part of the spectrum of signal Y is denoted as .

5. The workshop collaborative anomaly warning system based on dynamic association of multi-source environmental parameters according to claim 1, characterized in that, During the operation stage of the visualization module, the generated change trend graphs correspond one by one to various types of workshop environmental parameters, and the graphs representing the change trends of various types of workshop environmental parameters are line graphs, and the workshop environmental parameters represented in the line graphs are updated in real time based on the newly collected workshop environmental parameters by the operation of the collection module.

6. The workshop collaborative anomaly early warning system based on dynamic association of multi-source environmental parameters according to claim 1, wherein When the diagnosis module does not determine that the value represented in the change trend graph exceeds the corresponding warning threshold, it determines that the workshop operation is safe and synchronously refreshes the system operation; The lower level of the diagnosis module is provided with a monitoring unit and a picking unit. The monitoring unit is used to monitor whether the change trend graph of the numerical source exceeding the corresponding warning threshold is unique when it is determined that there is an operation risk in the workshop during the operation stage of the diagnosis module; Unique: Trigger the operation of the picking unit to pick the change trend graph that is most similar to the change trend graph of the numerical source exceeding the warning threshold; Not unique: Stop the operation of the workshop, coordinate and maintain the environment and equipment in the workshop to restore the environment and equipment in the workshop to the preset state; Among them, during the operation stage of the picking unit, the picking targets are the change trend graph of the numerical source exceeding the warning threshold, the change trend graph representing the vibration signal of the equipment in the workshop, and the change trend graph that is most similar to the change trend graph of the numerical source exceeding the warning threshold; When the picking targets are the change trend graph of the numerical source exceeding the warning threshold and the change trend graph representing the vibration signal of the equipment in the workshop are the same, only two groups of change trend graphs picked by the picking unit are picked, and the change trend graphs picked by the picking unit during operation are forwarded to the analysis module synchronously.

7. The workshop collaborative anomaly warning system based on dynamic association of multi-source environmental parameters according to claim 6, characterized in that, The similarity calculation logic of the change trend graph is expressed as: ； Wherein: is the similarity between the change trend graph a and the change trend graph b; , are the total number of nodes on the multi-segment broken lines representing values in the change trend graph a and the change trend graph b; is the coordination factor; is the total number of intersection nodes on the multi-segment broken lines representing values in the change trend graph a and the change trend graph b starting from the origin of the change trend graph towards the horizontal axis direction; , are the lengths of the line segments representing the q-th node to the (q + 1)-th node in the change trend graph a and the change trend graph b; , are the slopes of the line segments representing the q-th node to the (q + 1)-th node in the change trend graph a and the change trend graph b; Among them, represents the operation of taking the mean value of The value of the coordination factor is 1 or -1. If the numerator of the fraction where the coordination factor is located is less than or equal to the denominator, the value of the coordination factor is 1; otherwise, the value of the coordination factor is -1.

8. The workshop collaborative anomaly early warning system based on dynamic association of multi-source environmental parameters according to claim 6, characterized in that, The analysis logic of the workshop operation fault tendency in the analysis module is expressed as: ； Wherein: is the workshop operation fault tendency; is the difference in parameters in the numerical source change trend graph exceeding the warning threshold; is the difference in parameters in the change trend graph most similar to the numerical source change trend graph exceeding the warning threshold; is except and the total number of nodes in the change trend graph, excluding the change trend graph pointed to; is except and the warning threshold configured for the change trend graph, excluding the change trend graph pointed to; is the representation value of the v-th node; When there are only two sets of changing trend graphs picked up by the picking unit, the third product term in the logical formula for obtaining is replaced by the constant 1. When the difference calculation target in the formula is the vibration signal of equipment outside the workshop, its difference calculation logic is expressed as: Obtain the latest two values in the change trend graph, and denote them as MAX(I) and MIN(I) based on the magnitudes of the two values. Then the difference calculation logic is expressed as ; Among them, the fault determination thresholds set in the determination module correspond one by one to the environmental parameters of each workshop. When the determination module compares the fault determination threshold with the workshop operation fault tendency, it selects the workshop environmental parameter corresponding to the change trend graph of the numerical source exceeding the warning threshold during the operation stage of the diagnosis module to perform the comparison operation.

9. The workshop collaborative anomaly warning system based on dynamic association of multi-source environmental parameters according to claim 1, wherein, When the determination module determines that there is a fault in the workshop operation, the workshop stops operation, and the environment and equipment in the workshop are coordinated and maintained to restore the environment and equipment in the workshop to the preset state; When the determination module determines that there is no fault in the workshop operation, the equipment for managing the workshop environmental parameters corresponding to the change trend graph of the numerical source exceeding the warning threshold picked by the picking unit is used as the maintenance target for offline maintenance.

10. The workshop collaborative anomaly early warning system based on dynamic association of multi-source environmental parameters according to claim 1, wherein The acquisition module is interactively connected with the visualization module and the diagnosis module through a wireless network. The lower level of the diagnosis module is interactively connected with a monitoring unit and a picking unit through a wireless network. The diagnosis module is interactively connected with the analysis module and the determination module through a wireless network. The determination module is interactively connected with the message module through a wireless network.

Images