An industrial production monitoring and management system based on thermal imaging recognition

Abstract

The application relates to the technical field of industrial production monitoring, and discloses an industrial production monitoring management system based on thermal imaging recognition. The data acquisition module collects the temperature distribution image of industrial equipment and the environmental temperature and humidity in the industrial production process through a thermal imaging sensor. The data processing module obtains the temperature change data of each key region of the industrial equipment according to the temperature distribution image of the industrial equipment. Then, according to the influence of the environmental temperature and humidity, the temperature abnormal risk coefficients of each region of the industrial equipment are calculated according to the process temperature data collected periodically in the industrial production process, so that the temperature distribution of the industrial equipment in the industrial production process is accurately monitored. Meanwhile, the temperature abnormal conditions of each region are judged according to the temperature abnormal risk coefficients of each region. Then, the power of the cooling equipment corresponding to each region is adjusted according to the abnormal conditions of each region, so that the influence of the excessively high or low temperature on the industrial production is avoided.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of industrial production monitoring, and particularly relates to an industrial production monitoring management system based on thermal imaging recognition. BACKGROUND

[0002] In modern industrial production, it is crucial to ensure the safe, stable and efficient operation of the production line. Traditional monitoring methods often rely on contact sensors, which have safety hazards and response lags. With the rapid development of thermal imaging technology, its non-contact, wide-range and real-time characteristics provide a new solution for industrial production monitoring.

[0003] Existing industrial production monitoring management systems based on thermal imaging recognition mostly set reasonable temperature thresholds, compare the monitored temperature with the temperature threshold, and if the threshold requirement is not met, it means that the current temperature of the equipment is abnormal. However, this monitoring system has the following problems: 1. It does not consider the influence of environmental factors on equipment temperature; 2. It can only judge obvious abnormal points, and cannot rule out human or other factors that cause temperature abnormalities at a certain moment, which can easily lead to false positives. Therefore, the present application proposes an industrial production monitoring management system based on thermal imaging recognition. SUMMARY

[0004] The purpose of the present application is to provide an industrial production monitoring management system based on thermal imaging recognition to solve the above technical problems.

[0005] The purpose of the present application can be achieved by the following technical solutions:

[0006] An industrial production monitoring management system based on thermal imaging recognition, comprising a data acquisition module, a data processing module, a data analysis module, a temperature state evaluation and alarm module, and a cooling management module.

[0007] The data acquisition module comprises a plurality of thermal imaging sensors for acquiring industrial equipment temperature distribution images during industrial production, and temperature and humidity sensors for acquiring ambient temperature and humidity around the industrial equipment.

[0008] The data processing module is used to obtain temperature data of each position of the industrial equipment during production based on the industrial equipment temperature distribution images.

[0009] The data analysis module is used to analyze the temperature data of each position of the industrial equipment, the ambient temperature data around the industrial equipment, and the environmental humidity data.

[0010] The temperature state evaluation and alarm module is used for evaluating the temperature state of the industrial equipment according to the analysis result of the data analysis module, triggering an alarm immediately when the temperature is abnormal, and notifying the relevant personnel through short message, email and the like.

[0011] The cooling management module comprises a plurality of cooling devices, and is used for adjusting the cooling power according to the temperature state of the industrial equipment.

[0012] As a further description of the present application, the working process of the data acquisition module comprises:

[0013] The industrial equipment is divided into a plurality of regions, and each region is numbered, and the numbers are 1, 2, …, n in sequence;

[0014] The temperature distribution image of each region is acquired through the thermal imaging sensor;

[0015] The set threshold interval of each region is acquired.

[0016] As a further description of the present application, the working process of the data analysis module comprises:

[0017] The temperature threshold interval [T i1 , T i2 ] of the set i-th region is acquired;

[0018] The temperature data of the i-th region is collected every Δt time with Δt as an interval period;

[0019] The temperature change data of the i-th region of the industrial equipment with time is acquired, and a function T i (t) is fitted;

[0020] The temperature abnormal risk coefficient μ i of the i-th region is calculated by the following formula:

[0021]

[0022] In the formula, t1 is the initial monitoring time, t2 is the current monitoring time, y is the number of times that the temperature is less than or equal to T i1 , x is the number of times that the temperature is greater than or equal to T i2 , T(t j ) is the temperature data collected in the j-th period, T(t m ) is the temperature data collected in the m-th period, wherein j belongs to x and m belongs to y, T e (t2) is the current environmental influence degree, α, β and γ are preset weight coefficients, and μ i is the temperature abnormal risk coefficient of the i-th region.

[0023] As a further description of the present application, the current time environmental influence temperature T e The obtaining process of (t2) includes:

[0024] Obtaining current time environmental temperature data T W (t2) and environmental humidity data H W (t2);

[0025] Constructing a mathematical calculation model of the current time environmental influence degree T e (t2), and the expression is:

[0026]

[0027] In the formula, F() is an environmental humidity-environmental temperature conversion function, T W (t2) is the environmental temperature at t2, H W (t2) is the environmental humidity at t2, and ω is a preset weight coefficient.

[0028] As a further description of the present application, the working process of the temperature state evaluation and alarm module includes:

[0029] Comparing the i-th area temperature abnormality risk coefficient μ i with a preset i-th area temperature abnormality risk coefficient standard interval [μ i1 , μ i2 ];

[0030] If the i-th area temperature abnormality risk coefficient μ i does not belong to the interval [μ i1 , μ i2 ], it is judged that the i-th area temperature is abnormal, and the working equipment may be malfunctioning, and an alarm is triggered immediately, and relevant personnel are informed through short messages, emails, etc.

[0031] Otherwise, it is judged that the i-th area temperature is abnormal.

[0032] As a further description of the present application, the working process of the cooling management module includes:

[0033] When the i-th area temperature abnormality risk coefficient μ i is less than μ i1 , it is indicated that the i-th area temperature is too low, and the cooling power P i1 of the cooling equipment of the i-th area at this time is obtained.

[0034] The adjusted power of the cooling equipment of the i-th area is calculated by the following formula:

[0035]

[0036] Wherein, T0 is a preset standard environmental influence temperature, and δ is a conversion coefficient.

[0037] As further description of the present application, the working process of the cooling management module further includes:

[0038] When the temperature anomaly risk coefficient μ i of the i-th region is greater than μ i2 , it indicates that the temperature of the i-th region is too high, and the cooling power P i2 of the cooling device of the i-th region is obtained.

[0039] The adjusted power of the cooling device of the i-th region is calculated by the following formula:

[0040]

[0041] Wherein, T0 is a preset standard environmental influence temperature, and δ is a conversion coefficient.

[0042] As further description of the present application, the system further includes a thermal imaging sensor self-checking module, which is used for self-checking all thermal imaging sensors before industrial production, and the self-checking process includes:

[0043] The temperature change data of the h-th thermal imaging sensor over time during the self-checking process is obtained, and a temperature change function T h (t) is fitted.

[0044] The thermal imaging sensor self-checking coefficient α is calculated by the following formula:

[0045]

[0046] Wherein, z is the number of thermal imaging sensors, t3 is the initial time of self-checking, t4 is the end time of self-checking, T h (t4) is the temperature data collected by the h-th thermal imaging sensor at the end time of self-checking, and k is a preset weight coefficient.

[0047] The thermal imaging sensor self-checking coefficient α is compared with a preset thermal imaging sensor self-checking coefficient threshold τ th , and if the thermal imaging sensor self-checking coefficient α is greater than or equal to the thermal imaging sensor self-checking coefficient threshold τ th , it indicates that the h-th thermal imaging sensor has a fault.

[0048] The beneficial effects of the present application are: 1. In order to avoid the danger and error caused by the contact type sensor measurement, the data acquisition module collects the temperature distribution image of the industrial equipment and the environmental temperature and humidity in the industrial production process based on the thermal imaging sensor, the data processing module obtains the temperature change data of each key area of the industrial equipment according to the temperature distribution image of the industrial equipment, then, combined with the influence of the environmental temperature and humidity, the temperature abnormal risk coefficient of each area of the industrial equipment is calculated according to the periodically collected process temperature data in the industrial production process, the temperature distribution of the industrial equipment in the industrial production process is accurately monitored, and the temperature abnormality of each area is judged according to the temperature abnormal risk coefficient of each area, then, the power of the cooling equipment corresponding to each area is adjusted according to the abnormality of each area, so as to avoid the influence of too high or too low temperature on industrial production;

[0049] 2. The present application performs self-checking on all thermal imaging sensors before the start of industrial production, avoids affecting the monitoring of industrial equipment in the industrial production process, and the temperature monitored by the thermal imaging sensor in the self-checking process is the environmental temperature, the difference between the average change of the collected temperature of each thermal imaging sensor in the self-checking process and the collected temperature change of the corresponding thermal imaging sensor and the difference between the real-time collected temperature of each thermal imaging sensor and the collected temperature of the corresponding thermal imaging sensor are calculated to obtain the thermal imaging sensor self-checking coefficient, the thermal imaging sensor self-checking coefficient is compared with the preset thermal imaging sensor self-checking coefficient threshold value, if the thermal imaging sensor self-checking coefficient is greater than or equal to the thermal imaging sensor self-checking coefficient threshold value, it means that the current thermal imaging sensor has a fault. BRIEF DESCRIPTION OF DRAWINGS

[0050] The present application will be further described below in combination with the drawings.

[0051] Figure 1 The present application provides a structure schematic diagram of an industrial production monitoring management system based on thermal imaging recognition. DETAILED DESCRIPTION

[0052] The technical solutions in the embodiments of the present application will be clearly and completely described below in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0053] Please refer to Figure 1 The present application is an industrial production monitoring management system based on thermal imaging recognition, comprising a data acquisition module, a data processing module, a data analysis module, a temperature state evaluation and alarm module and a cooling management module.

[0054] The data acquisition module comprises a plurality of thermal imaging sensors for acquiring temperature distribution images of the industrial equipment in the industrial production process, and further comprises temperature sensors and humidity sensors for acquiring ambient temperature and humidity of the industrial equipment;

[0055] The data processing module is configured to acquire temperature data of each position of the industrial equipment according to the temperature distribution images of the industrial equipment.

[0056] The data analysis module is configured to analyze the temperature data of each position of the industrial equipment, the ambient temperature data and the ambient humidity data of the industrial equipment.

[0057] The temperature state evaluation and alarm module is configured to evaluate the temperature state of the industrial equipment according to the analysis result of the data analysis module, and trigger an alarm and notify relevant personnel through short message, email or the like when an abnormal temperature is found.

[0058] The cooling management module comprises a plurality of cooling devices for adjusting the cooling power according to the temperature state of the industrial equipment.

[0059] According to the above technical solution, the temperature distribution images of the industrial equipment and the ambient temperature and humidity in the industrial production process are acquired by the thermal imaging sensors of the data acquisition module to avoid the danger and error caused by the contact type sensor measurement, the temperature change data of each key region of the industrial equipment is acquired according to the temperature distribution images of the industrial equipment by the data processing module, then the temperature abnormal risk coefficients of each region of the industrial equipment are calculated according to the periodically acquired process temperature data in the industrial production process in combination with the influence of the ambient temperature and humidity, the accurate monitoring of the temperature distribution of the industrial equipment in the industrial production process is realized, the temperature abnormality of each region is judged according to the temperature abnormal risk coefficients of each region, then the power of the cooling device corresponding to each region is adjusted according to the abnormality of each region to avoid the influence of the excessively high or low temperature on the industrial production.

[0060] As a further description of the present application, the working process of the data acquisition module comprises:

[0061] The industrial equipment is divided into a plurality of regions, the regions include motor, battery, production line and the like, and each region is numbered, the numbering is 1, 2, …, n in turn;

[0062] The temperature distribution images of each region are acquired by the thermal imaging sensors.

[0063] The threshold interval of each region is acquired.

[0064] As a further description of the present application, the working process of the data analysis module comprises:

[0065] Get the set temperature threshold range [T] for the i-th region. i1 T i2 ];

[0066] Temperature data for the i-th region is collected at intervals of Δt.

[0067] Obtain the temperature variation data of the i-th region of the industrial equipment over time, and fit the function T. i (t);

[0068] The temperature anomaly risk coefficient μ for the i-th region is calculated using the following formula. i :

[0069]

[0070] In the formula, t1 is the initial monitoring time, t2 is the current monitoring time, and y represents the temperature less than or equal to T. i1 The number of times, x is the temperature greater than or equal to T. i2 The number of times, T(t) j T(t) represents the temperature data collected in the j-th cycle. m Let be the temperature data collected in the m-th cycle, where j belongs to x, m belongs to y, and T e (t2) represents the environmental impact at the current time, where α, β, and γ are preset weighting coefficients, and μ i Let be the temperature anomaly risk coefficient for the i-th region.

[0071] As a further description of the present invention, the current environmental influence temperature T e The process of obtaining (t2) includes:

[0072] Get the ambient temperature data T at the current moment. W (t2) and ambient humidity data H W (t2);

[0073] Construction of environmental impact T e (t2) Mathematical calculation model, expression:

[0074]

[0075] In the formula, F() is the ambient humidity-ambient temperature conversion function, and T W (t2) represents the ambient temperature at time t2, H. W (t2) represents the ambient humidity at time t2. ω and ω are preset weighting coefficients.

[0076] As a further description of the present invention, the working process of the temperature status assessment and alarm module includes:

[0077] The i-th region temperature anomaly risk coefficient μ i is compared with a preset i-th region temperature anomaly risk coefficient standard interval [μ i1 , μ i2 ];

[0078] If the i-th region temperature anomaly risk coefficient μ i does not belong to the interval [μ i1 , μ i2 ], it is judged that the i-th region temperature is abnormal, and the working equipment may fail, an alarm is triggered immediately, and relevant personnel are notified by means of short message, email, etc.

[0079] Otherwise, it is judged that the i-th region temperature is abnormal.

[0080] Through the above technical solution, the i-th region temperature data is collected every Δt time, the collection result is compared with the preset i-th region temperature threshold interval, according to the number of i-th region temperatures less than the lower limit of the interval and the number of i-th region temperatures greater than the upper limit of the interval, the influence of the environmental temperature and the environmental humidity on the environmental temperature is combined, the temperature anomaly risk coefficient of the i-th region is calculated, the i-th region temperature anomaly risk coefficient is compared with the preset i-th region temperature anomaly risk coefficient standard interval, if the i-th region temperature anomaly risk coefficient μ i does not belong to the preset interval, it is judged that the i-th region temperature is abnormal, and the working equipment may fail, an alarm is triggered immediately, and relevant personnel are notified by means of short message, email, etc.

[0081] As a further description of the present application, the working process of the cooling management module includes:

[0082] When the i-th region temperature anomaly risk coefficient μ i is less than μ i1 , it indicates that the i-th region temperature is too low, and the cooling power P i1 of the cooling equipment of the i-th region at this time is obtained.

[0083] The adjusted power of the cooling equipment of the i-th region is calculated by the following formula:

[0084]

[0085] In the formula, T0 is a preset standard environmental influence temperature, and δ is a conversion coefficient.

[0086] As a further description of the present application, the working process of the cooling management module further includes:

[0087] When the i-th region temperature anomaly risk coefficient μ i is greater than μ i2When the temperature in region i is too high, the cooling power P of the cooling equipment in region i is obtained. i2 ;

[0088] The adjusted power of the cooling equipment in the i-th region is calculated using the following formula:

[0089]

[0090] In the formula, T0 is the preset standard ambient temperature, and δ is the conversion coefficient.

[0091] Through the above technical solution, this embodiment uses the temperature anomaly risk coefficient μ of the i-th region. i The cooling power of the cooling equipment is adjusted according to the relationship with the preset interval. When the temperature anomaly risk coefficient μ of the i-th region is... i Less than μ i1 When the temperature in the i-th region is too low, it indicates that the cooling power needs to be reduced. This is determined by considering the real-time environmental influence on the temperature and using the formula... Calculate the adjusted power, when the temperature anomaly risk coefficient μ of the i-th region... i Greater than μ i2 When the temperature in region i is too high, it indicates that the cooling power needs to be increased. This is determined by considering the real-time environmental influence on the temperature and using the formula... The calculated and adjusted power ensures that the temperature in each area of ​​the equipment is within the set range, preventing excessively high or low temperatures that could affect the normal operation of the industrial equipment.

[0092] As a further description of the present invention, the system also includes a thermal imaging sensor self-test module, which is used to perform self-tests on all thermal imaging sensors before industrial production. The self-test process includes:

[0093] Acquire the temperature change data of the h-th thermal imaging sensor over time during the self-test process, and fit the temperature change function T over time. h (t);

[0094] The self-test coefficient of the thermal imaging sensor is calculated using the following formula. :

[0095]

[0096] In the formula, z represents the number of thermal imaging sensors, t3 is the initial time of self-test, t4 is the end time of self-test, and T... h (t4) represents the temperature data collected by the h-th thermal imaging sensor at the end of the self-test, and k is a preset weighting coefficient.

[0097] Self-test coefficient of thermal imaging sensor With the preset thermal imaging sensor self-test coefficient threshold τ thComparatively, if the thermal imaging sensor self-checking coefficient is greater than or equal to a thermal imaging sensor self-checking coefficient threshold τ th , it indicates that the hth thermal imaging sensor has a fault.

[0098] Through the above technical solution, the embodiment performs self-checking on all thermal imaging sensors before industrial production starts, avoids affecting the monitoring of industrial equipment in the industrial production process, and the temperature monitored by the thermal imaging sensor in the self-checking process is the ambient temperature. The difference between the average change of the cumulative change of the collection temperature of each thermal imaging sensor in the self-checking process and the cumulative change of the collection temperature of the corresponding thermal imaging sensor and the difference between the real-time condition of the collection temperature of each thermal imaging sensor and the collection temperature of the corresponding thermal imaging sensor is used to calculate the thermal imaging sensor self-checking coefficient. The thermal imaging sensor self-checking coefficient is compared with the preset thermal imaging sensor self-checking coefficient threshold, and if the thermal imaging sensor self-checking coefficient is greater than or equal to the thermal imaging sensor self-checking coefficient threshold, it indicates that the current thermal imaging sensor has a fault.

[0099] It should be noted that all weight coefficients, thresholds and threshold intervals in the present application are obtained based on empirical data, and do not need to be described in detail.

[0100] The above has described one embodiment of the present application in detail, but the content described is only the preferred embodiment of the present application, and cannot be considered as limiting the scope of the present application. Any equivalent changes and improvements made in the scope of the present application should still belong to the patent coverage of the present application.

Claims

1. An industrial production monitoring management system based on thermal imaging recognition, characterized in that, The system comprises a data acquisition module, a data processing module, a data analysis module, a temperature state evaluation and alarm module and a cooling management module. The data acquisition module comprises a plurality of thermal imaging sensors for acquiring temperature distribution images of industrial equipment in an industrial production process, and temperature sensors and humidity sensors for acquiring ambient temperature and humidity of the industrial equipment. The data processing module is configured to acquire temperature data of each position of the industrial equipment according to the temperature distribution images of the industrial equipment. The data analysis module is configured to analyze the temperature data of each position of the industrial equipment, the ambient temperature data and the humidity data. The temperature state evaluation and alarm module is configured to evaluate the temperature state of the industrial equipment according to the analysis result of the data analysis module, and trigger an alarm and notify relevant personnel by means of short message and email as soon as an abnormal temperature is found. The cooling management module comprises a plurality of cooling devices for adjusting cooling power according to the temperature state of the industrial equipment. The working process of the data analysis module comprises: Get the set temperature threshold range [T] for the i-th region. i1 T i2 ]; Collecting temperature data of the ith region at intervals of Δt; Obtain the time-varying data of the temperature of the i-th region of the industrial equipment, and fit a function T i (t); The temperature anomaly risk coefficient μ of the i-th region is calculated by the following formula i : In the formula, t1 is the initial monitoring time, t2 is the current monitoring time, y is the number of times when the temperature is less than or equal to T i1 , x is the number of times when the temperature is greater than or equal to T i2 , T(t j ) is the temperature data collected in the jth period, T(t m ) is the temperature data collected in the mth period, j belongs to x, m belongs to y, T e (t2) is the current time environmental influence degree, alpha, beta and gamma are preset weight coefficients, mu i is the temperature abnormality risk coefficient of the ith region. The current time environment influence temperature T e The acquisition process of (t2) includes: acquiring current time environment temperature data T W (t2) and environment humidity data H W (t2); Construction time environmental impact degree T e (t2) mathematical calculation model, expression is: In the formula, F() is an ambient humidity-ambient temperature conversion function, T W (t2) is the ambient temperature at time t2, H W (t2) is the ambient humidity at time t2, and ω is a preset weight coefficient. The system further comprises a thermal imaging sensor self-checking module, which is configured to perform self-checking on all thermal imaging sensors before industrial production. acquiring temperature versus time data of the hth thermal imaging sensor during a self-test and fitting a temperature versus time function T h (t); The thermal imaging sensor self-checking coefficient is calculated by the following formula : In the formula, z is the number of thermal imaging sensors, t3 is the initial time of self-checking, t4 is the end time of self-checking, T h (t4) is the temperature data collected by the hth thermal imaging sensor at the end time of self-checking, and k is a preset weight coefficient. Thermal imaging sensor self-checking coefficient comparing with preset thermal imaging sensor self-checking coefficient threshold τ th comparing with preset thermal imaging sensor self-checking coefficient threshold τ comparing with preset thermal imaging sensor self-checking coefficient threshold τ th thermal imaging sensor self-checking coefficient is greater than or equal to thermal imaging sensor self-checking coefficient threshold τ 2. The industrial production monitoring management system based on thermal imaging recognition according to claim 1, characterized in that, The working process of the data acquisition module comprises: Dividing the industrial equipment into a plurality of regions and numbering each region, with the numbering being 1, 2, …, n in sequence; Acquiring temperature distribution images of each region by means of thermal imaging sensors; Acquiring a set threshold interval for each region.

3. The industrial production monitoring management system based on thermal imaging recognition according to claim 1, characterized in that, The working process of the temperature state evaluation and alarm module comprises: comparing the temperature abnormality risk coefficient μ i of the i-th region with a preset temperature abnormality risk coefficient standard interval [μ i1 , μ i2 ] of the i-th region; If the temperature anomaly risk coefficient μ i of the i-th region is not in the interval [μ i1 , μ i2 ], it is determined that the temperature of the i-th region is abnormal, an alarm is triggered immediately, and relevant personnel are notified by SMS or email. Otherwise, judging that the temperature of the ith region is abnormal.

4. The industrial production monitoring management system based on thermal imaging recognition according to claim 1, characterized in that, The working process of the cooling management module comprises: When the temperature anomaly risk coefficient μ i of the i-th region is less than μ i1 , it indicates that the temperature of the i-th region is too low, and the cooling power P i1 of the cooling device of the i-th region is obtained. Calculating the adjusted power of the cooling device of the ith region by the following formula: In the formula, T0 is a preset standard ambient temperature, and δ is a conversion coefficient.

5. The industrial production monitoring management system based on thermal imaging recognition according to claim 4, characterized in that, The working process of the cooling management module further comprises: When the temperature anomaly risk coefficient μ i of the i-th region is greater than μ i2 , it indicates that the temperature of the i-th region is too high, and the cooling power P i2 of the cooling device of the i-th region is obtained. Calculating the adjusted power of the cooling device of the ith region by the following formula: In the formula, T0 is a preset standard ambient temperature, and δ is a conversion coefficient.

Images