Robot patrol system based on machine vision

Abstract

The invention relates to the technical field of patrol, and discloses a robot patrol system based on machine vision, which is connected with a plurality of monitoring sensing systems of a robot through a network, and numbering and classifying data monitored by the monitoring sensing systems. A machine image data set, a machine smoke data set, a machine gas data set and a machine temperature data set are formed, then the current environment danger coefficient is analyzed according to the data sets, whether danger exists or not is judged according to the environment danger coefficient, and a signal is sent to the warning module when danger exists. Meanwhile, an electric quantity analysis module is connected with a machine battery system to estimate the electric quantity required by machine operation, whether the current electric quantity can support machine inspection completion or not is judged according to an estimation result, and a signal is sent to a charging module when it is judged that the electric quantity cannot support machine inspection completion, so that the working efficiency and safety are comprehensively improved; and the robot can smoothly complete the established patrol task.

Description

Technical Field

[0001] The present invention relates to the field of patrol technology, and in particular to a robot patrol system based on machine vision. Background Art

[0002] Inspection is a systematic activity that aims to ensure the safety and compliance of specific areas, facilities or processes through regular or irregular inspections. The main purpose of inspection is to promptly identify problems and potential risks so that appropriate preventive or corrective measures can be taken. It is an important management and supervision method that can not only help organizations to promptly identify and solve problems, but also improve overall operational efficiency and safety. Inspection plays an indispensable role in industrial production, medical services and public safety. The current inspection method mainly relies on manpower. Regularly or irregularly arranging personnel to patrol in specific areas to detect whether there are any abnormal problems plays a vital role in enterprises.

[0003] In the existing manual inspection process, significant problems can be discovered in a timely manner, and corresponding emergency treatment plans can be implemented according to the problems found. However, manual inspection consumes time and energy. At the same time, in specific areas, dust and anti-static treatment is required inside the area, which increases the tediousness of manual inspection. Summary of the invention

[0004] 1. Technical issues to be solved

[0005] In view of the shortcomings of the prior art, the present invention provides a robot inspection system based on machine vision, which has the advantages of improving work efficiency and safety, being able to work continuously, not being restricted by time, place and environment, being more efficient than manual inspection, reducing dependence on manpower, adapting to various complex environments and terrains, improving work efficiency and safety, and being able to more accurately assess the degree of danger of the environment through comprehensive analysis, helping to avoid task interruptions due to power exhaustion, and ensuring that the robot can successfully complete the established inspection tasks, etc.

[0006] (II) Technical solution

[0007] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: a robot inspection system based on machine vision, comprising a machine data feedback module, the machine data feedback module is connected to multiple monitoring sensor systems of the robot through a network, and the data monitored by the monitoring sensor system are numbered and classified to form a machine image data set, a machine smoke data set, a machine gas data set and a machine temperature data set, the machine data feedback module is connected to a machine data analysis module and a power analysis module through a network, and the machine data feedback module feeds back the monitored data to the machine data analysis module;

[0008] The machine data analysis module analyzes the current environmental risk factor according to the machine image data set, the machine smoke data set, the machine gas data set, and the machine temperature data set, and determines whether there is a danger according to the environmental risk factor, and sends a signal to the warning module if there is a danger;

[0009] The power analysis module estimates the power required for the machine to operate by connecting to the machine battery system, and determines whether the current power can support the completion of the machine inspection based on the estimation result. If it is determined that the power cannot support the completion of the machine inspection, a signal is sent to the charging module.

[0010] Preferably, the robot's multiple monitoring sensing systems include a camera device, a smoke sensor, a gas sensor and a temperature sensor. The camera device is used to collect and monitor the image in front of the robot during the robot's patrol process, the smoke sensor is used to collect and monitor the smoke concentration in the robot's environment during the robot's patrol process, the gas sensor is used to collect and monitor the gas concentration in the robot's environment during the robot's patrol process, and the temperature sensor is used to collect and monitor temperature data in the robot's environment during the robot's patrol process.

[0011] Preferably, the expression of the machine image data set is: Tx1, Tx2, Tx3, . . . , Tx n , the expression of the machine smoke data set is: Yw1, Yw2, Yw3, ···, Yw n , the expression of the machine gas data set is: Qt1, Qt2, Qt3, . . . , Qt n , the expression of the machine temperature data set is: Wd1, Wd2, Wd3, . . . , Wd n In the above expression, 1 to n correspond to the number of data in the data set, and the collection time of 1 to n data in each data set is consistent.

[0012] Preferably, the environmental risk factor includes machine image blur, smoke concentration excess value, gas concentration excess value, and temperature standard deviation value.

[0013] Preferably, the machine image fuzziness is calculated as follows:

[0014]

[0015] In the above formula, TXmh is the machine image blur, Tx q is the standard definition of the image in the current environment, Tx i is the actual definition of the current image, Tx o It is the lowest clarity of the current image standard in the historical data.

[0016] The calculation method of the smoke concentration exceeding the standard value is:

[0017]

[0018] In the above formula, YWnd is the smoke concentration exceeding the standard value, Yw q is the standard smoke concentration, Yw i is the current smoke density.

[0019] The calculation method of the excess gas concentration value is:

[0020]

[0021] In the above formula, WTnd represents the excess gas concentration, Qt q Represents the gas concentration under standard conditions, Qt i Represents the current gas concentration.

[0022] The temperature standard deviation is calculated as follows:

[0023]

[0024] In the above formula, WDcz represents the temperature standard deviation. Represents the mean value of the temperature data in the temperature data set, Wd i Represents the current temperature data.

[0025] Preferably, the expression of the environmental risk factor is:

[0026]

[0027] In the above formula, ω1, ω2, ω3, and ω4 represent the corresponding weight factors of the machine image blur, the smoke concentration exceeding the standard value, and the gas concentration exceeding the standard value, respectively.

[0028] Preferably, when any one of the machine image blurriness, smoke concentration exceeding standard value, and gas concentration exceeding standard value exceeds the corresponding threshold value, the machine data analysis module issues a low-level danger warning to the warning module;

[0029] When any two of the machine image blurriness, smoke concentration exceeding standard value, and gas concentration exceeding standard value exceed corresponding thresholds, the machine data analysis module issues an intermediate danger warning to the warning module;

[0030] When any three values ​​of the machine image blur, smoke concentration exceeding the standard value, and gas concentration exceeding the standard value exceed the corresponding threshold value, the machine data analysis module issues a medium or high-level danger warning to the warning module;

[0031] When all the values ​​of the machine image blur, smoke concentration exceeding the standard value, and gas concentration exceeding the standard value exceed the corresponding thresholds, or when the environmental hazard coefficient exceeds the environmental hazard threshold, a high-level hazard warning is sent to the warning module.

[0032] Preferably, the warning module is connected to a buzzer unit and an information unit, and the warning module sends out different buzzer warnings according to the danger warning level and the intrusion signal, and sends information to emergency response personnel at the same time.

[0033] Preferably, the calculation formula for the amount of electricity required for the machine to run is as follows:

[0034]

[0035] In the above formula, DLsx represents the power required for the machine to run, SYdl represents the remaining power of the current battery system, CSdl represents the initial power, DQjl represents the current running distance, ZYjl represents the total distance of this inspection, and FHyl represents the reserved power of the robot charging path. It represents the amount of electricity required to complete this inspection, and p is the weight factor.

[0036] Preferably, when the calculated result of the amount of electricity required for the operation of the machine is less than or equal to 0, it means that the current amount of electricity is unable to support the completion of the machine inspection, and a charging signal is sent to the charging module.

[0037] Compared with the prior art, the present invention provides a robot inspection system based on machine vision, which has the following beneficial effects:

[0038] 1. The robot of the present invention uses video equipment, smoke sensors, gas sensors and temperature sensors for monitoring during the inspection process, which can significantly improve its work efficiency and safety. It can work continuously without being restricted by time, place and environment. It is more efficient than manual inspection and reduces dependence on manual labor. It can adapt to various complex environments and terrains, improve work efficiency and safety, and provide comprehensive and accurate data support for management personnel, which is helpful to timely discover and deal with various safety hazards, and then calculate the environmental hazard factor and conduct corresponding evaluation alarms, so as to facilitate comprehensive analysis and more accurately evaluate the degree of danger of the environment, thereby avoiding the false alarm or missed alarm phenomenon that may occur in a single sensor, which is very important for preventing the occurrence of accidents such as fire and explosion. At the same time, according to different levels of signal alarms, timely reminders of the danger level are given, so that corresponding emergency measures can be taken according to the danger level.

[0039] 2. The present invention can predict whether the remaining power is sufficient to complete the current task or return to the charging station by evaluating the amount of power required for the machine to run, which helps to avoid task interruptions due to power exhaustion and ensures that the robot can successfully complete the established inspection tasks. At the same time, in high-risk environments, such as chemical plants, mines and other places, insufficient power may cause the robot to suddenly stop working, increasing safety risks. Traditional manual inspections require regular checks on the robot's power status, and the power estimation function can reduce this burden, allowing managers to focus more on other important tasks and avoid frequent charging or task interruptions due to insufficient power, thereby improving work efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 It is a schematic diagram of the structural system of the present invention; DETAILED DESCRIPTION

[0041] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0042] See also Figure 1 , a robot inspection system based on machine vision, including a machine data feedback module, the machine data feedback module is connected to multiple monitoring sensor systems of the robot through a network, and the data monitored by the monitoring sensor system is numbered and classified to form a machine image data set, a machine smoke data set, a machine gas data set and a machine temperature data set, the machine data feedback module is connected to a machine data analysis module and a power analysis module through a network, and the machine data feedback module feeds back the monitored data to the machine data analysis module;

[0043] The robot's multiple monitoring sensor systems include camera equipment, smoke sensors, gas sensors and temperature sensors. The camera equipment is used to collect and monitor the image in front of the robot during the robot's patrol process. The smoke sensor is used to collect and monitor the smoke concentration in the robot's environment during the robot's patrol process. The gas sensor is used to collect and monitor the gas concentration in the robot's environment during the robot's patrol process. The temperature sensor is used to collect and monitor the temperature data in the robot's environment during the robot's patrol process.

[0044] The robot uses video equipment, smoke sensors, gas sensors and temperature sensors for monitoring during the inspection process, which can significantly improve its work efficiency and safety. It can work continuously without being restricted by time, location and environment. Compared with manual inspection, it is more efficient and reduces dependence on manual labor, especially in high-risk environments, which reduces labor costs and safety risks. The various sensors carried can provide accurate and timely data, avoiding the influence of human subjective factors. It can work in high-risk environments such as high temperature and high pressure, flammable and explosive, and adapt to various complex environments and terrains, improving work efficiency and safety. It also provides comprehensive and accurate data support for managers, which helps to timely discover and deal with various safety hazards.

[0045] The expression of the machine image dataset is: Tx1, Tx2, Tx3, ···, Tx n , the expression of the machine smoke data set is: Yw1, Yw2, Yw3, ···, Yw n , the expression of the machine gas data set is: Qt1, Qt2, Qt3, ···, Qt n , the expression of the machine temperature data set is: Wd1, Wd2, Wd3, ···, Wd n ,In the above expression, 1~n correspond to the number of data in the data set, and the collection time of 1~n data in each data set is consistent;

[0046] The machine data analysis module analyzes the current environmental risk factor based on the machine image data set, the machine smoke data set, the machine gas data set, and the machine temperature data set, and determines whether there is a danger based on the environmental risk factor, and sends a signal to the warning module if there is a danger;

[0047] Environmental risk factors include machine image blur, smoke concentration exceeding the standard, gas concentration exceeding the standard, and temperature standard deviation;

[0048] The calculation method of machine image blur is:

[0049]

[0050] In the above formula, Txmh is the machine image blur, Tx q is the standard definition of the image in the current environment, Tx i is the actual definition of the current image, Tx o It is the lowest clarity of the current image standard in the historical data.

[0051] The calculation method of smoke concentration exceeding the standard is:

[0052]

[0053] In the above formula, YWnd is the smoke concentration exceeding the standard value, Yw q is the standard smoke concentration, Yw i is the current smoke density.

[0054] The calculation method of the excess gas concentration is:

[0055]

[0056] In the above formula, QTnd represents the excess gas concentration, Qt q Represents the gas concentration under standard conditions, Tt i Represents the current gas concentration.

[0057] The temperature standard deviation is calculated as:

[0058]

[0059] In the above formula, WDcz represents the temperature standard deviation. Represents the mean value of the temperature data in the temperature data set, Wd i Represents the current temperature data;

[0060] The expression of environmental risk factor is:

[0061]

[0062] In the above formula, ω1, ω2, ω3, and ω4 represent the corresponding weight factors of the machine image blur, the smoke concentration exceeding the standard value, and the gas concentration exceeding the standard value respectively;

[0063] When any of the machine image blur, smoke concentration exceeding the standard value, and gas concentration exceeding the standard value exceeds the corresponding threshold, the machine data analysis module issues a low-level danger warning to the warning module;

[0064] When any two values ​​of the machine image blur, smoke concentration exceeding the standard value, and gas concentration exceeding the standard value exceed the corresponding threshold, the machine data analysis module issues an intermediate danger warning to the warning module;

[0065] When any three values ​​of the machine image blur, smoke concentration exceeding the standard value, and gas concentration exceeding the standard value exceed the corresponding threshold, the machine data analysis module issues a medium or high-level danger warning to the warning module;

[0066] When all values ​​of the machine image blur, smoke concentration exceeding the standard value, and gas concentration exceeding the standard value exceed the corresponding threshold, or when the environmental hazard factor exceeds the environmental hazard threshold, a high-level hazard warning is sent to the warning module;

[0067] The warning module is connected to a buzzer unit and an information unit. The warning module issues different buzzer warnings according to the danger warning level and the intrusion signal, and sends information to emergency response personnel at the same time;

[0068] The machine calculates the environmental risk factor based on the image blur, smoke concentration exceeding the standard value, gas concentration exceeding the standard value, and temperature standard deviation, and makes corresponding assessment alarms, so as to facilitate comprehensive analysis and more accurately assess the degree of environmental risk, thereby avoiding the false alarm or missed alarm phenomenon that may occur in a single sensor, which is crucial for preventing accidents such as fire and explosion. At the same time, according to different levels of signal alarms, timely remind the danger level, so as to facilitate the corresponding emergency measures according to the danger level;

[0069] The power analysis module estimates the power required for the machine to run by connecting to the machine battery system, and determines whether the current power can support the machine to complete the inspection based on the estimated results. If it is determined that the power cannot support the machine to complete the inspection, it sends a signal to the charging module;

[0070] The formula for calculating the amount of electricity required to run the machine is as follows:

[0071]

[0072] In the above formula, DLsx represents the power required for the machine to run, SYdl represents the remaining power of the current battery system, CSdl represents the initial power, DQjl represents the current running distance, ZYjl represents the total distance of this inspection, and FHyl represents the reserved power of the robot charging path. represents the amount of electricity required to complete this inspection, and p is the weight factor;

[0073] When the calculated result of the power required for the machine to run is less than or equal to 0, it means that the current power cannot support the machine to complete the inspection, and a charging signal is sent to the charging module.

[0074] By evaluating the amount of power required for machine operation, it is possible to predict whether the remaining power is sufficient to complete the current task or return to the charging station, which helps avoid task interruptions due to power exhaustion and ensures that the robot can successfully complete the established inspection tasks. At the same time, in high-risk environments, such as chemical plants and mines, insufficient power may cause the robot to suddenly stop working, increasing safety risks. Traditional manual inspections require regular checks of the robot's power status, and the power estimation function can reduce this burden, allowing managers to focus more on other important tasks and avoid frequent charging or task interruptions due to insufficient power, thereby improving work efficiency.

[0075] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A robot inspection system based on machine vision, characterized in that: It includes a machine data feedback module, which is connected to multiple monitoring sensor systems of the robot through a network, and numbers and classifies the data monitored by the monitoring sensor systems to form a machine image data set, a machine smoke data set, a machine gas data set, and a machine temperature data set. The machine data feedback module is connected to a machine data analysis module and a power analysis module through a network, and the machine data feedback module feeds back the monitored data to the machine data analysis module; The machine data analysis module analyzes the current environmental risk factor according to the machine image data set, the machine smoke data set, the machine gas data set, and the machine temperature data set, and determines whether there is a danger according to the environmental risk factor, and sends a signal to the warning module if there is a danger; The power analysis module estimates the power required for the machine to operate by connecting to the machine battery system, and determines whether the current power can support the completion of the machine inspection based on the estimation result. If it is determined that the power cannot support the completion of the machine inspection, a signal is sent to the charging module.

2. The machine vision-based robot inspection system according to claim 1, characterized in that: The robot's multiple monitoring sensing systems include a camera device, a smoke sensor, a gas sensor and a temperature sensor. The camera device is used to collect and monitor the image in front of the robot during the robot's patrol process. The smoke sensor is used to collect and monitor the smoke concentration in the robot's environment during the robot's patrol process. The gas sensor is used to collect and monitor the gas concentration in the robot's environment during the robot's patrol process. The temperature sensor is used to collect and monitor the temperature data in the robot's environment during the robot's patrol process.

3. The robot inspection system based on machine vision according to claim 2, characterized in that: The expression of the machine image data set is: Tx1, Tx2, Tx3, ..., Tx n , the expression of the machine smoke data set is: Yw1, Yw2, Yw3, ..., Yw n , the expression of the machine gas data set is: Qt1, Qt2, Qt3, ..., Qt n , the expression of the machine temperature data set is: Wd1, Wd2, Wd3, ..., Wd n In the above expression, 1 to n correspond to the number of data in the data set, and the collection time of 1 to n data in each data set is consistent.

4. The machine vision-based robot inspection system according to claim 3, characterized in that: The environmental risk factors include machine image blur, smoke concentration exceeding the standard value, gas concentration exceeding the standard value, and temperature standard deviation value.

5. The machine vision-based robot inspection system according to claim 4, characterized in that: The calculation method of the machine image fuzziness is: In the above formula, TXmh is the machine image blur, Tx q is the standard definition of the image in the current environment, Tx i is the actual definition of the current image, Tx o It is the lowest clarity of the current image standard in the historical data. The calculation method of the smoke concentration exceeding the standard value is: In the above formula, YWnd is the smoke concentration exceeding the standard value, Yw q is the standard smoke concentration, Yw i is the current smoke density. The calculation method of the excess gas concentration is as follows: In the above formula, QTnd represents the excess gas concentration, Qt q Represents the gas concentration under standard conditions, Qt i Represents the current gas concentration. The temperature standard deviation is calculated as follows: In the above formula, WDcz represents the temperature standard deviation. Represents the mean value of the temperature data in the temperature data set, Wd i Represents the current temperature data.

6. The machine vision-based robot inspection system according to claim 5, characterized in that: The expression of the environmental risk factor is: In the above formula, ω1, ω2, ω3, and ω4 represent the corresponding weight factors of the machine image blur, the smoke concentration exceeding the standard value, and the gas concentration exceeding the standard value, respectively.

7. The machine vision-based robot inspection system according to claim 6, characterized in that: When any one of the machine image blurriness, smoke concentration exceeding standard value, and gas concentration exceeding standard value exceeds the corresponding threshold, the machine data analysis module issues a low-level danger warning to the warning module; When any two of the machine image blurriness, smoke concentration exceeding standard value, and gas concentration exceeding standard value exceed corresponding thresholds, the machine data analysis module issues an intermediate danger warning to the warning module; When any three values ​​of the machine image blur, smoke concentration exceeding the standard value, and gas concentration exceeding the standard value exceed the corresponding threshold value, the machine data analysis module issues a medium or high-level danger warning to the warning module; When all the values ​​of the machine image blur, smoke concentration exceeding the standard value, and gas concentration exceeding the standard value exceed the corresponding thresholds, or when the environmental hazard coefficient exceeds the environmental hazard threshold, a high-level hazard warning is sent to the warning module.

8. The machine vision-based robot inspection system according to claim 7, characterized in that: The warning module is connected with a buzzer unit and an information unit. The warning module sends out different buzzer warnings according to the danger warning level and the intrusion signal, and sends information to emergency response personnel at the same time.

9. The robot inspection system based on machine vision according to claim 1, characterized in that: The calculation formula for the amount of electricity required to run the machine is as follows: In the above formula, DLsx represents the power required for the machine to run, SYdl represents the remaining power of the current battery system, CSdl represents the initial power, DQjl represents the current running distance, ZYjl represents the total distance of this inspection, and FHyl represents the reserved power of the robot charging path. It represents the amount of electricity required to complete this inspection, and p is the weight factor.

10. The machine vision-based robot inspection system according to claim 9, characterized in that: When the calculated result of the power required for the machine to run is less than or equal to 0, it means that the current power is unable to support the machine to complete the inspection, and a charging signal is sent to the charging module.

Images