Chemical safety inspection system and method based on multi-data fusion

Through multi-data fusion technology, real-time monitoring of the operating status of chemical safety inspection robots has been solved, and the problem that traditional systems cannot predict the failure of inspection robots is improved, data accuracy and user experience are achieved, and more efficient inspections are achieved.

CN118965243AActive Publication Date: 2024-11-15ZHICHUANG KONAN (HANGZHOU) TECH CO LTD

Patent Information

Application Number
CN202411442918.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-10-16
Publication Date
2024-11-15
Estimated Expiration
2044-10-16

AI Technical Summary

Technical Problem

Traditional chemical safety inspection systems cannot monitor the operation status of the inspection robot itself in real time, resulting in uncertain data acquisition and affecting the accuracy of monitoring.

Method used

Using multi-data fusion technology, we can obtain physical data and historical operation data of mobile platforms, robotic arms and perception equipment, build corresponding digital models, and use monitoring models to monitor and preprocess data in real time, output abnormal alarm signals, and judge patrol robot failures. .

Benefits of technology

It improves the accuracy of inspection data and the maintainability of the system, promptly detects potential safety hazards or failures, avoids affecting inspections, and enhances user experience and problem positioning capabilities.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118965243A_ABST
    Figure CN118965243A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of chemical safety inspection, in particular to a chemical safety inspection system and method based on multi-data fusion, which is applied to a safety inspection robot and comprises the following steps: constructing a mobile platform digital model and a mechanical arm digital model; constructing a corresponding sensing equipment digital model; establishing communication connection among the safety inspection robot, the sensing equipment and the central server; a sensing equipment data monitoring module I and a state monitoring module I are integrated in the mobile platform digital model, and a sensing equipment data monitoring module II and a state monitoring module II are integrated in the mechanical arm digital model; sensing equipment data are monitored through a sensing equipment data monitoring module I and a sensing equipment data monitoring module II; the running state data of the mobile platform and the running state data of the mechanical arm are monitored through a state monitoring module I and a state monitoring module II; chemical equipment data, mobile platform operation state data and mechanical arm operation state data are monitored through the monitoring model, and an alarm signal is sent out when abnormity is monitored.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of chemical safety inspection, and in particular to a chemical safety inspection system and method based on multi-data fusion. Background Art

[0002] The chemical production environment has extremely high requirements for safety monitoring due to its complexity and potential dangers. Traditional inspection methods rely on manual inspections, which are not only inefficient but also pose safety risks. For this reason, many chemical companies use chemical safety inspection robots to replace manual inspections. Chemical safety inspection robots conduct inspections in the inspection area according to preset inspection routes, monitor the environmental data around chemical equipment and equipment operation data, and remotely transmit the data to the monitoring center for processing. However, the traditional inspection system cannot predict the failure of the inspection robot itself, resulting in the data sent back cannot be guaranteed to be obtained when the inspection robot is working normally, affecting the accuracy of monitoring.

[0003] To this end, we propose a chemical safety inspection system and method based on multi-data fusion. Summary of the invention

[0004] The present invention is based on multi-data fusion technology and can monitor the operating status of the inspection robot in real time. At the same time, the operating data of the inspection equipment (safety inspection robot) itself is taken into account during the monitoring process to optimize the prediction model and improve the accuracy of monitoring.

[0005] The technical solution proposed by the present invention is: a chemical safety inspection method based on multi-data fusion, the method comprising: The safety inspection robot comprises a mobile platform, a mechanical arm and a plurality of sensing devices, and is characterized in that the method comprises: Obtain the physical data and historical operation data of the mobile platform and the robotic arm, and build a digital model of the mobile platform and the robotic arm respectively; Obtain the physical data and historical operation data of multiple sensing devices and build corresponding digital models of the sensing devices; Establish communication connection between security inspection robots, sensing devices and central servers; Integrate the perception device data monitoring module 1 and the state monitoring module 1 in the digital model of the mobile platform, and integrate the perception device data monitoring module 2 and the state monitoring module 2 in the digital model of the robotic arm; The sensory device data is obtained from the central server through the sensory device data monitoring module 1 and the sensory device data monitoring module 2 respectively, and the obtained sensory device data is pre-processed and then output; The mobile platform operation status data and the robotic arm operation status data are obtained from the central server through the state monitoring module 1 and the state monitoring module 2, and the obtained mobile platform operation status data and the robotic arm operation status data are pre-processed and then output; The monitoring model monitors the perception device data, mobile platform operation status data and robotic arm operation status data, outputs abnormal alarm signals and regulates the robotic arm operation status.

[0006] Preferably, the sensing device includes an environment sensing module and an operation state sensing module, the environment sensing module includes a sound collection device, a gas concentration sensor, an infrared camera and a high-definition camera; the operation state sensing module includes a distance sensor, a speed sensor, and an angle encoder 1 and an angle encoder 2 installed on the outside of the mobile platform; The angle encoder 1 and the angle encoder 2 are used to obtain the horizontal rotation angle data and the pitch angle data of the robot arm respectively; the digital model of the sensing device includes a digital model of a sound collection device, a digital model of a gas concentration sensor, a digital model of an infrared camera, a digital model of a high-definition camera, a digital model of a distance sensor, a digital model of a speed sensor, a digital model of an angle encoder 1 and a digital model of an angle encoder 2; The method of acquiring the sensing device data from the central server by using the sensing device data monitoring module 1 and the sensing device data monitoring module 2 respectively includes the following steps: Establishing data connection between the first and second sensing device data monitoring modules and the central server; The central server obtains monitoring data from the environmental perception module according to the preset collection frequency and adds a collection timestamp of one to form a monitoring data set; Extracting sound signals and gas concentration data from the monitoring data set through the sensing device data monitoring module 1; Infrared image data and high-definition image data are extracted from the monitoring data set through the perception device data monitoring module 2.

[0007] Preferably, the pre-processing and outputting of the acquired sensing device data comprises the following steps: The acquired gas concentration data is deduplicated, de-noised and outliers are removed to form a gas concentration data set; The sound signal is converted into the frequency domain through Fourier transform, and the frequency mean and standard deviation frequency values ​​are extracted to form the voiceprint data set; Establishing a plurality of display tags one, and associating the plurality of display tags one with the digital model of the sensing device; Performing noise removal on the infrared image data and the high-definition image data to form an infrared image data set and a high-definition image data set; Associating the voiceprint dataset, the gas concentration dataset, the infrared image dataset, and the high-definition image dataset with corresponding display tags respectively; By displaying label one, the digital model of the sensory device can display the corresponding sensory device data information.

[0008] Preferably, the obtaining of the mobile platform operation status data and the mechanical arm operation status data from the central server through the state monitoring module 1 and the state monitoring module 2 comprises the following steps: Establish data connection between status monitoring module 1, status monitoring module 2 and central server; The central server obtains the operation data from the operation status perception module according to the preset collection frequency, and adds the collection timestamp 2 to form a status data set; Extract distance data and mobile platform movement data from the state data set through the state monitoring module 1; Extracting the horizontal rotation angle data and the pitch angle data of the robot arm from the state data set through the state monitoring module 2; The step of pre-processing and outputting the acquired mobile platform operation status data and mechanical arm operation status data comprises the following steps: The acquired distance data, mobile platform movement data, robot arm horizontal angle data, and robot arm pitch angle data are preprocessed to form a distance data set, a movement speed data set, a horizontal angle data set, and a pitch angle data set; Establish multiple display tags 2 and display tags 3, associate the multiple display tags 2 with the mobile platform digital model, and associate the multiple display tags 3 with the robot arm digital model respectively; Associating the distance dataset and the moving speed dataset with corresponding display label 2 respectively; Associating the horizontal angle dataset and the pitch angle dataset with corresponding display labels three respectively; By displaying label 2, the digital model of the mobile platform can display data information of the moving speed and the distance to the obstacle; By displaying label three, the digital model of the robotic arm can display horizontal angle and pitch angle data information.

[0009] Preferably, monitoring the sensing device data, the mobile platform operating status data and the robotic arm operating status data through the monitoring model comprises the following steps: Building a monitoring model ;in, , They represent intercept 1, intercept 2, intercept 3 and intercept 4 respectively. They represent error term 1, error term 2, error term 3, and error term 4 respectively; are all multidimensional vectors, representing regression coefficient vector 1, regression coefficient vector 2, regression coefficient vector 3 and regression coefficient vector 4 respectively; Indicates the predicted value of equipment failure probability. represents the predicted value of equipment failure probability 2; represents the predicted value of mobile platform failure probability, represents the predicted value of the robot arm failure probability, , , and represents the input vector; Constructing a sound feature vector set, a gas concentration feature vector set, a mobile platform speed feature vector set, and a robotic arm motion state feature vector set; The data in the voiceprint key feature vector set is normalized and input into ; ; They are sound coefficient one and sound coefficient two respectively; The data in the gas concentration feature vector set are normalized and input into ; ; They are gas concentration coefficient one and gas concentration coefficient two respectively; The data in the mobile platform velocity feature vector set is normalized and input into ; ; They are speed factor one and speed factor two respectively; The data in the robot arm motion state feature vector set is normalized and input into ; ; They are angle coefficient one and angle coefficient two respectively; Set the device safety probability threshold And the safety probability threshold of the inspection robot ; if , it is determined that a safety fault has occurred in the equipment, a safety alarm signal is output, and the infrared image and the high-definition image with a time stamp of 5 seconds before and after are extracted from the infrared image data set and the high-definition image data set; and the display color of the digital model of the sound collection device and the digital model of the gas concentration sensor is changed; if , it is determined that the inspection robot has a fault, a maintenance alarm signal is issued, and the display colors of the speed sensor digital model, the angle encoder 1 digital model and the angle encoder 2 digital model are changed; wherein, They are weight value one, weight value two, weight value three and weight value four respectively.

[0010] Preferably, the constructing of the sound feature vector set, the gas concentration feature vector set, the mobile platform speed feature vector set and the robotic arm motion state feature vector set comprises the following steps: Set sliding window one; A plurality of frequency means and standard deviations are selected from the voiceprint data set through a sliding window, and a voiceprint feature vector is formed after normalization, and a plurality of voiceprint feature vectors are obtained by moving the sliding window one multiple times, and the plurality of voiceprint feature vectors form a sound feature vector set; Select multiple gas concentration values ​​from the gas concentration data set through a sliding window, extract the average gas concentration value and the maximum gas concentration value, and form a gas concentration feature vector after normalization; obtain multiple gas concentration key feature vectors by moving the sliding window multiple times, and the multiple gas concentration key feature vectors constitute a gas concentration feature vector set; Set sliding window 2; Extracting the highest speed and the average speed from the mobile speed data set through sliding window 2, forming a mobile platform speed feature vector after normalization, obtaining multiple mobile platform speed feature vectors by moving sliding window 1 multiple times, and the multiple mobile platform speed feature vectors forming a mobile platform speed feature vector set; Select multiple horizontal angles from the horizontal angle data set through sliding window 2, and calculate the average change rate of the horizontal angles; obtain multiple pitch angle data from the pitch angle data set through sliding window 2, and calculate the average change rate of the pitch angles; normalize the average change rate of the horizontal angle and the average change rate of the pitch angle to form a motion state vector of the robot arm; A plurality of robot arm motion state vectors are obtained by sliding the window multiple times, and the plurality of robot arm motion state vectors constitute a robot arm motion state feature vector set.

[0011] Preferably, the calculation is performed to obtain The average value of the gas concentration within the sliding window and the maximum gas concentration , move the sliding window multiple times to form a gas concentration feature vector set: ; Calculate the first The average of the frequency means within a sliding window The mean and standard deviation of the frequency values , move the sliding window multiple times to form a sound feature vector set: ; Calculate the first The maximum speed within the sliding window and average speed , move the sliding window multiple times to form a mobile platform speed feature vector set: ; Calculate the first The average change rate of the horizontal angle within a sliding window is: and the average rate of change of pitch angle , move the sliding window multiple times to form a mobile platform speed feature vector set: ;in, Indicates the number of times sliding window 1 and sliding window 2 move; , ,in Indicates Horizontal angle value, Indicates Pitch angle value, .

[0012] Preferably, the historical safety alarm signal output data and the historical maintenance alarm signal issuance data are obtained from the database, and the number of historical maintenance alarm signal issuances within 2 minutes before and after the historical safety alarm signal output is counted to calculate the confidence , which is used to reflect the probability of equipment safety alarm caused by failure of the inspection robot, so as to optimize the monitoring model. .

[0013] The present invention also provides a chemical safety inspection system based on multiple data fusion, and the system is used to execute the chemical safety inspection method based on multiple data fusion.

[0014] The present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the chemical safety inspection method based on multi-data fusion.

[0015] Beneficial effects of the present invention: 1. The present invention acquires the physical data and historical operation data of the mobile platform, the mechanical arm and a plurality of sensing devices, constructs a corresponding digital model, provides support for subsequent monitoring and management, integrates the sensing device data monitoring module and the state monitoring module in the digital model of the mobile platform and the digital model of the mechanical arm, respectively, improves the maintainability and scalability of the system, and enables each module to work independently and without interfering with each other. The monitoring model monitors the environmental data and the state (heating or vibration) of the chemical equipment in the sensing inspection area in real time, as well as the operating state data of the mobile platform and the operating state data of the mechanical arm, and outputs an abnormal alarm signal when an abnormality is detected, which helps to timely discover potential safety hazards or fault problems during the inspection process. According to the output results of the monitoring model, the operating state of the mechanical arm can also be monitored to determine whether the inspection robot is faulty, and the inspection robot fault can be discovered in time to avoid affecting the normal inspection function. The action of the mechanical arm can also be adjusted remotely according to actual needs to avoid unnecessary collision, damage or inadequate inspection action, so that the camera and sensor cannot effectively obtain environmental and equipment data, thereby improving the efficiency of the inspection.

[0016] 2. The present invention realizes real-time data acquisition of the digital model of the mobile platform and the digital model of the mechanical arm by establishing data connections between the sensor device data monitoring module 1 and the sensor device data monitoring module 2 and the central server. Timely data updates are ensured, so that the digital model can quickly reflect environmental changes and equipment status in the inspection area; by establishing multiple display tags 1 and associating these tags with the sensor device digital model, intuitive display of data is achieved. This enables users to understand the operating status and monitoring data of each device at a glance, enhancing user experience and facilitating rapid problem location and decision-making.

[0017] 3. In the present invention, the data input into the monitoring model includes voiceprint feature data, gas concentration feature data, mobile platform speed feature data, and robotic arm motion state feature data. The data of multiple sensors are integrated to establish the association between voiceprint and gas concentration features and chemical equipment failures, as well as the association between changes in mobile platform speed and robotic arm rotation angle and robotic arm status. At the same time, through statistical analysis of historical data, the association between inspection robot failures and equipment safety alarms is established, thereby optimizing the monitoring model to obtain an optimized monitoring model, thereby improving the accuracy of the early warning of the monitoring model. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 The present invention is a flow chart of a chemical safety inspection method based on multi-data fusion. DETAILED DESCRIPTION

[0019] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art can think of other obvious variations. The basic principles of the present invention defined in the following description can be applied to other embodiments, variations, improvements, equivalents, and other technical solutions that do not deviate from the spirit and scope of the present invention.

[0020] It is to be understood that the term "one" should be understood as "at least one" or "one or more", that is, in one embodiment, the number of an element may be one, while in another embodiment, the number of the element may be multiple, and the term "one" should not be understood as a limitation on the quantity.

[0021] Nowadays, chemical plants mostly use chemical safety inspection robots to replace manual inspections. The robots inspect corresponding areas of the chemical plants according to preset inspection routes. The present invention is also based on the existing chemical safety inspection robots.

[0022] refer to Figure 1 The technical solution provided by the present invention is: a chemical safety inspection method based on multi-data fusion, applied to a safety inspection robot, the safety inspection robot includes a mobile platform, a mechanical arm and a plurality of sensing devices, the sensing devices include an environment sensing module and an operation state sensing module, the environment sensing module includes a sound collection device, a gas concentration sensor, an infrared camera and a high-definition camera; the operation state sensing module includes a distance sensor, a speed sensor and an angle encoder 1 and an angle encoder 2 installed on the outside of the mobile platform; Angle encoder 1 and angle encoder 2 are used to obtain the horizontal rotation angle data and pitch angle data of the robot arm respectively.

[0023] The digital models of sensing equipment include the digital models of sound collection devices, gas concentration sensors, infrared cameras, high-definition cameras, distance sensors, speed sensors, angle encoders 1 and angle encoders 2. All digital models can be combined with the digital models of mobile platforms and robotic arms according to their actual positions on the safety inspection robot. They can also be displayed independently without being combined with the digital models of mobile platforms and robotic arms.

[0024] The method comprises the following steps: Step 1: Obtain the physical data and historical operation data of the mobile platform and the robotic arm, and construct a digital model of the mobile platform and a digital model of the robotic arm respectively; Step 2: Obtain the physical data and historical operation data of multiple sensing devices and build corresponding digital models of the sensing devices; Step 3: Establish communication connection between security inspection robot, sensing device and central server; Step 4: Integrate the perception device data monitoring module 1 and the state monitoring module 1 into the digital model of the mobile platform, and integrate the perception device data monitoring module 2 and the state monitoring module 2 into the digital model of the robotic arm; Step 5: Acquire the sensory device data from the central server through the sensory device data monitoring module 1 and the sensory device data monitoring module 2 respectively, and pre-process the acquired sensory device data before outputting it, which specifically includes the following steps: Establishing data connection between the first and second sensing device data monitoring modules and the central server; The central server obtains monitoring data from the environmental perception module according to the preset collection frequency and adds a collection timestamp of one to form a monitoring data set; Extracting sound signals and gas concentration data from the monitoring data set through the sensing device data monitoring module 1; Extract infrared image data and high-definition image data from the monitoring data set through the perception device data monitoring module 2; The acquired gas concentration data is deduplicated, de-noised and outliers are removed to form a gas concentration data set; The sound signal is converted into the frequency domain through Fourier transform, and the frequency mean and standard deviation frequency values ​​are extracted to form the voiceprint data set; Establishing a plurality of display tags one, and associating the plurality of display tags one with the digital model of the sensing device; Performing noise removal on the infrared image data and the high-definition image data to form an infrared image data set and a high-definition image data set; Associating the voiceprint dataset, the gas concentration dataset, the infrared image dataset, and the high-definition image dataset with corresponding display tags respectively; By displaying label one, the digital model of the sensory device can display the corresponding sensory device data information.

[0025] In this embodiment, the association between display label 1 and sensory device can be realized by Python programming, specifically: first, a dictionary named datasets is created, including different types of sensory device data. Then, a dictionary named display_labels is created to map each dataset type to the corresponding display label 1. Then, a function named display_data is defined, which accepts a display label 1 as a parameter, retrieves the corresponding data from the datasets dictionary according to the label, and prints it out. Finally, when the user selects a different display label 1, the display_data function is called to display the corresponding data.

[0026] Step 6: Obtain the mobile platform operation status data and the robotic arm operation status data from the central server through the status monitoring module 1 and the status monitoring module 2, and pre-process the obtained mobile platform operation status data and the robotic arm operation status data before outputting them, which specifically includes the following steps: Establish data connection between status monitoring module 1, status monitoring module 2 and central server; The central server obtains the operation data from the operation status perception module according to the preset collection frequency, and adds the collection timestamp 2 to form the state data set. The distance data and mobile platform movement data are extracted from the state data set through the state monitoring module 1; the horizontal angle data and the pitch angle data of the robotic arm are extracted from the state data set through the state monitoring module 2.

[0027] The acquired distance data, mobile platform movement data, robot arm horizontal angle data and robot arm pitch angle data are preprocessed to form a distance data set, a movement speed data set, a horizontal angle data set and a pitch angle data set. Multiple display labels 2 and display labels 3 are established, and multiple display labels 2 are associated with the mobile platform digital model, and multiple display labels 3 are associated with the robot arm digital model. The distance data set and the movement speed data set are associated with the corresponding display label 2 respectively. The horizontal angle data set and the pitch angle data set are associated with the corresponding display label 3 respectively. The mobile platform digital model can display the movement speed and the distance data information of the distance obstacle by displaying label 2. The robot arm digital model can display the horizontal angle and pitch angle data information by displaying label 3.

[0028] Step 7: Monitor the sensing device data, the mobile platform operation status data and the robot arm operation status data through the monitoring model, output abnormal alarm signals and adjust the robot arm operation status. The monitoring model in this embodiment is constructed based on the regression algorithm, and specifically includes the following steps: The following steps are involved: Building a monitoring model ;in, , They represent intercept 1, intercept 2, intercept 3 and intercept 4 respectively. They represent error term 1, error term 2, error term 3, and error term 4 respectively; are all multidimensional vectors, representing regression coefficient vector 1, regression coefficient vector 2, regression coefficient vector 3 and regression coefficient vector 4 respectively; It should be noted that the specific training process of the monitoring model in this embodiment can refer to the training process of the existing regression algorithm model, and the training process will not be repeated here. The following process of predicting faults through the model uses the trained monitoring model.

[0029] Indicates the predicted value of equipment failure probability. represents the predicted value of equipment failure probability 2; represents the predicted value of mobile platform failure probability, represents the predicted value of the robot arm failure probability, , , and represents the input vector; Construct the sound feature vector set, gas concentration feature vector set, mobile platform speed feature vector set and robotic arm motion state feature vector set, specifically: The following steps are involved: A sliding window is set, and multiple frequency means and standard deviations are selected from the voiceprint data set through the sliding window, and the voiceprint feature vector is formed after normalization. Multiple voiceprint feature vectors are obtained by moving the sliding window one multiple times, and the multiple voiceprint feature vectors form a sound feature vector set; multiple gas concentration values ​​are selected from the gas concentration data set through the sliding window one, and the average gas concentration value and the maximum gas concentration value are extracted, and the gas concentration feature vector is formed after normalization; multiple gas concentration key feature vectors are obtained by moving the sliding window one multiple times, and the multiple gas concentration key feature vectors form a gas concentration feature vector set; A sliding window 2 is set, and the maximum speed and the average speed are extracted from the mobile speed data set through the sliding window 2, and the normalized ones form a mobile platform speed feature vector. Multiple mobile platform speed feature vectors are obtained by moving the sliding window 1 multiple times, and the multiple mobile platform speed feature vectors form a mobile platform speed feature vector set; multiple horizontal angles are selected from the horizontal angle data set through the sliding window 2, and the average change rate of the horizontal angles is calculated; multiple pitch angle data are obtained from the pitch angle data set through the sliding window 2, and the average change rate of the pitch angle is calculated; the average change rate of the horizontal angle and the average change rate of the pitch angle are normalized to form a manipulator motion state vector; multiple manipulator motion state vectors are obtained by sliding the window 2 multiple times, and the multiple manipulator motion state vectors form a manipulator motion state feature vector set.

[0030] In some preferred embodiments, the calculation obtains the first The average value of the gas concentration within the sliding window and the maximum gas concentration , move the sliding window multiple times to form a gas concentration feature vector set: ; Calculate the first The average of the frequency means within a sliding window The mean and standard deviation of the frequency values , move the sliding window multiple times to form a sound feature vector set: ; Calculate the first The maximum speed within the sliding window and average speed , move the sliding window multiple times to form a mobile platform speed feature vector set: ; Calculate the first The average change rate of the horizontal angle within a sliding window is: and the average rate of change of pitch angle , move the sliding window multiple times to form a mobile platform speed feature vector set: ;in, Indicates the number of times sliding window 1 and sliding window 2 move; , ,in Indicates Horizontal angle value, Indicates Pitch angle value, .

[0031] The data in the voiceprint key feature vector set is normalized and input into ; ; They are sound coefficient one and sound coefficient two respectively; The data in the gas concentration feature vector set are normalized and input into ; ; They are gas concentration coefficient one and gas concentration coefficient two respectively; The data in the mobile platform velocity feature vector set is normalized and input into ; ; They are speed factor one and speed factor two respectively; The data in the robot arm motion state feature vector set is normalized and input into ; ; They are angle coefficient one and angle coefficient two respectively; Set the device safety probability threshold And the safety probability threshold of the inspection robot ; if , it is determined that the equipment has a safety failure, a safety alarm signal is output, and the infrared image and high-definition image 5 seconds before and after the timestamp are extracted from the infrared image data set and the high-definition image data set; and the display color of the digital model of the sound collection device and the digital model of the gas concentration sensor are changed; specifically, the display color of the digital model of the sound collection device and the digital model of the gas concentration sensor can be changed by modifying the properties of the relevant models. For example, the color attribute of the model can be set to red or other warning colors to remind the staff that the corresponding sensor data is abnormal.

[0032] if , it is determined that the inspection robot has a fault, a maintenance alarm signal is issued, and the display colors of the speed sensor digital model, the angle encoder 1 digital model and the angle encoder 2 digital model are changed; wherein, They are weight value one, weight value two, weight value three and weight value four respectively.

[0033] Obtain historical safety alarm signal output data and historical maintenance alarm signal issuance data from the database, count the number of historical maintenance alarm signal issuances within 2 minutes before and after the historical safety alarm signal output, and calculate the confidence level , which is used to reflect the probability of equipment safety alarm (false alarm) caused by failure of the inspection robot. For example, the collected data is inaccurate due to the inadequate rotation angle of the robot arm, or the distance between the mobile platform and the chemical equipment in the inspection area is not appropriate, which causes inaccurate collected data. In this way, the monitoring model is optimized and the monitoring accuracy is improved. , the rest of the expressions in the monitoring model remain unchanged.

[0034] The present invention also provides a chemical safety inspection system based on multiple data fusion, and the system is used to execute the chemical safety inspection method based on multiple data fusion.

[0035] The present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the chemical safety inspection method based on multi-data fusion.

[0036] The embodiments disclosed in the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. The embodiments disclosed in the present invention include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part, and / or installed from a removable medium. When the computer program is executed by the central processing unit (CPU), the above-mentioned functions defined in the method of the present application are executed. It should be noted that the above-mentioned computer-readable medium of the present application can be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium can be, for example, but not limited to, a system, device or device of an electrical, magnetic, optical, electromagnetic, infrared segment, or semiconductor, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection with one or more wire segments, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, electrical wire, optical cable, RF, etc., or any suitable combination of the foregoing.

[0037] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0038] Those skilled in the art should understand that the embodiments of the present invention described above and shown in the accompanying drawings are only examples and do not limit the present invention. The objectives of the present invention have been fully and effectively achieved. The functional and structural principles of the present invention have been demonstrated and explained in the embodiments. Without departing from the principles, the implementation methods of the present invention may be deformed or modified in any way.

Claims

1. A chemical safety inspection method based on multi-data fusion, applied to a safety inspection robot, wherein the safety inspection robot comprises a mobile platform, a mechanical arm and a plurality of sensing devices, characterized in that: The method comprises: Obtain the physical data and historical operation data of the mobile platform and the robotic arm, and build a digital model of the mobile platform and the robotic arm respectively; Obtain the physical data and historical operation data of multiple sensing devices and build corresponding digital models of the sensing devices; Establish communication connection between security inspection robots, sensing devices and central servers; Integrate the perception device data monitoring module 1 and the state monitoring module 1 in the digital model of the mobile platform, and integrate the perception device data monitoring module 2 and the state monitoring module 2 in the digital model of the robotic arm; The sensory device data is obtained from the central server through the sensory device data monitoring module 1 and the sensory device data monitoring module 2 respectively, and the obtained sensory device data is pre-processed and then output; The mobile platform operation status data and the robotic arm operation status data are obtained from the central server through the state monitoring module 1 and the state monitoring module 2, and the obtained mobile platform operation status data and the robotic arm operation status data are pre-processed and then output; The monitoring model monitors the perception device data, mobile platform operation status data and robotic arm operation status data, outputs abnormal alarm signals, and regulates the robotic arm operation status.

2. A chemical safety inspection method based on multi-data fusion according to claim 1, characterized in that: The sensing device includes an environment sensing module and an operation state sensing module. The environment sensing module includes a sound collection device, a gas concentration sensor, an infrared camera and a high-definition camera. The operation state sensing module includes a distance sensor, a speed sensor, and an angle encoder 1 and an angle encoder 2 installed on the outside of the mobile platform. The angle encoder 1 and the angle encoder 2 are used to obtain the horizontal rotation angle data and the pitch angle data of the robot arm respectively; the digital model of the sensing device includes a digital model of a sound collection device, a digital model of a gas concentration sensor, a digital model of an infrared camera, a digital model of a high-definition camera, a digital model of a distance sensor, a digital model of a speed sensor, a digital model of an angle encoder 1 and a digital model of an angle encoder 2; The method of acquiring the sensing device data from the central server by using the sensing device data monitoring module 1 and the sensing device data monitoring module 2 respectively includes the following steps: Establishing data connection between the first and second sensing device data monitoring modules and the central server; The central server obtains monitoring data from the environmental perception module according to the preset collection frequency and adds a collection timestamp of one to form a monitoring data set; Extracting sound signals and gas concentration data from the monitoring data set through the sensing device data monitoring module 1; Infrared image data and high-definition image data are extracted from the monitoring data set through the perception device data monitoring module 2.

3. A chemical safety inspection method based on multi-data fusion according to claim 2, characterized in that: The step of preprocessing and outputting the acquired sensing device data comprises the following steps: The acquired gas concentration data is deduplicated, de-noised and outliers are removed to form a gas concentration data set; The sound signal is converted into the frequency domain through Fourier transform, and the frequency mean and standard deviation frequency values ​​are extracted to form the voiceprint data set; Establishing a plurality of display tags one, and associating the plurality of display tags one with the digital model of the sensing device; Performing noise removal on the infrared image data and the high-definition image data to form an infrared image data set and a high-definition image data set; Associating the voiceprint dataset, the gas concentration dataset, the infrared image dataset, and the high-definition image dataset with corresponding display tags respectively; By displaying label one, the digital model of the sensory device can display the corresponding sensory device data information.

4. A chemical safety inspection method based on multi-data fusion according to claim 3, characterized in that: The method of obtaining the mobile platform operation status data and the mechanical arm operation status data from the central server through the state monitoring module 1 and the state monitoring module 2 includes the following steps: Establish data connection between status monitoring module 1, status monitoring module 2 and central server; The central server obtains the operation data from the operation status perception module according to the preset collection frequency, and adds the collection timestamp 2 to form a status data set; Extract distance data and mobile platform movement data from the state data set through the state monitoring module 1; Extracting the horizontal rotation angle data and the pitch angle data of the robot arm from the state data set through the state monitoring module 2; The step of pre-processing and outputting the acquired mobile platform operation status data and mechanical arm operation status data comprises the following steps: The acquired distance data, mobile platform movement data, robot arm horizontal angle data, and robot arm pitch angle data are preprocessed to form a distance data set, a movement speed data set, a horizontal angle data set, and a pitch angle data set; Establish multiple display tags 2 and display tags 3, associate the multiple display tags 2 with the mobile platform digital model, and associate the multiple display tags 3 with the robot arm digital model respectively; Associating the distance dataset and the moving speed dataset with corresponding display label 2 respectively; Associating the horizontal angle dataset and the pitch angle dataset with corresponding display labels three respectively; By displaying label 2, the digital model of the mobile platform can display data information of the moving speed and the distance to the obstacle; By displaying label three, the digital model of the robotic arm can display horizontal angle and pitch angle data information.

5. A chemical safety inspection method based on multi-data fusion according to claim 4, characterized in that: The monitoring of the sensing device data, the mobile platform operation status data and the robotic arm operation status data by the monitoring model comprises the following steps: Building a monitoring model ;in, , They represent intercept 1, intercept 2, intercept 3 and intercept 4 respectively. They represent error term 1, error term 2, error term 3, and error term 4 respectively; are all multidimensional vectors, representing regression coefficient vector 1, regression coefficient vector 2, regression coefficient vector 3 and regression coefficient vector 4 respectively; Indicates the predicted value of equipment failure probability. represents the predicted value of equipment failure probability 2; represents the predicted value of mobile platform failure probability, represents the predicted value of the robot arm failure probability, , , and Respectively represent the input vector; Constructing a sound feature vector set, a gas concentration feature vector set, a mobile platform speed feature vector set, and a robotic arm motion state feature vector set; The data in the voiceprint key feature vector set is normalized and input into ; ; They are sound coefficient one and sound coefficient two respectively; The data in the gas concentration feature vector set are normalized and input into ; ; They are gas concentration coefficient one and gas concentration coefficient two respectively; The data in the mobile platform velocity feature vector set is normalized and input into ; ; They are speed factor one and speed factor two respectively; The data in the robot arm motion state feature vector set is normalized and input into ; ; They are angle coefficient one and angle coefficient two respectively; Set the device safety probability threshold And the safety probability threshold of the inspection robot ; if , it is determined that a safety fault has occurred in the equipment, a safety alarm signal is output, and the infrared image and the high-definition image with a time stamp of 5 seconds before and after are extracted from the infrared image data set and the high-definition image data set; and the display color of the digital model of the sound collection device and the digital model of the gas concentration sensor is changed; if , it is determined that the inspection robot has a fault, a maintenance alarm signal is issued, and the display colors of the speed sensor digital model, the angle encoder 1 digital model and the angle encoder 2 digital model are changed; wherein, They are weight value one, weight value two, weight value three and weight value four respectively.

6. A chemical safety inspection method based on multi-data fusion according to claim 5, characterized in that: The step of constructing the sound feature vector set, the gas concentration feature vector set, the mobile platform speed feature vector set, and the robotic arm motion state feature vector set comprises the following steps: Set sliding window one; A plurality of frequency means and standard deviations are selected from the voiceprint data set through a sliding window, and a voiceprint feature vector is formed after normalization, and a plurality of voiceprint feature vectors are obtained by moving the sliding window one multiple times, and the plurality of voiceprint feature vectors form a sound feature vector set; Select multiple gas concentration values ​​from the gas concentration data set through a sliding window, extract the average gas concentration value and the maximum gas concentration value, and form a gas concentration feature vector after normalization; obtain multiple gas concentration key feature vectors by moving the sliding window multiple times, and the multiple gas concentration key feature vectors constitute a gas concentration feature vector set; Set sliding window 2; Extracting the highest speed and the average speed from the mobile speed data set through sliding window 2, forming a mobile platform speed feature vector after normalization, obtaining multiple mobile platform speed feature vectors by moving sliding window 1 multiple times, and the multiple mobile platform speed feature vectors forming a mobile platform speed feature vector set; Select multiple horizontal angles from the horizontal angle data set through sliding window 2, and calculate the average change rate of the horizontal angles; obtain multiple pitch angle data from the pitch angle data set through sliding window 2, and calculate the average change rate of the pitch angles; normalize the average change rate of the horizontal angle and the average change rate of the pitch angle to form a motion state vector of the robot arm; A plurality of robot arm motion state vectors are obtained by sliding the window multiple times, and the plurality of robot arm motion state vectors constitute a robot arm motion state feature vector set.

7. A chemical safety inspection method based on multi-data fusion according to claim 6, characterized in that: Calculate the first The average value of the gas concentration within the sliding window and the maximum gas concentration , move the sliding window multiple times to form a gas concentration feature vector set: ; Calculate the first The average of the frequency means within a sliding window The mean and standard deviation of the frequency values , move the sliding window multiple times to form a sound feature vector set: ; Calculate the first The maximum speed within the sliding window and average speed , move the sliding window multiple times to form a mobile platform speed feature vector set: ; Calculate the first The average change rate of the horizontal angle within a sliding window is: and the average rate of change of pitch angle , move the sliding window multiple times to form a mobile platform speed feature vector set: ;in, Indicates the number of times sliding window 1 and sliding window 2 move; , ,in Indicates Horizontal angle value, Indicates Pitch angle value, .

8. A chemical safety inspection method based on multi-data fusion according to claim 7, characterized in that: Obtain historical safety alarm signal output data and historical maintenance alarm signal issuance data from the database, count the number of historical maintenance alarm signal issuances within 2 minutes before and after the historical safety alarm signal output, and calculate the confidence level , which is used to reflect the probability of equipment safety alarm caused by failure of the inspection robot, so as to optimize the monitoring model. ,in, is the correction factor, .

9. A chemical safety inspection system based on multi-data fusion, characterized in that: The system is used to execute a chemical safety inspection method based on multi-data fusion as described in any one of claims 1 to 8 above.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement a chemical safety inspection method based on multi-data fusion as described in any one of claims 1 to 8.

Citation Information

Patent Citations

  • Control system for transformer substation patrol robot

    CN105259899A

  • Fault detection positioning and safety evaluation method for chemical industry park inspection robot

    CN110889455A

  • Intelligent inspection robot for detecting running micro-leakage of power plant equipment and detection method thereof

    CN110977964A

  • Intelligent robot inspection system and method

    CN110989594A

  • Field station intelligent robot inspection system and method

    CN112213979A

Cited By

  • Mobile robot scene dynamic rendering method based on WEB end 3D technology

    CN119399347A

  • Data acquisition system of robot

    CN120245000A