Multi-source infrared remote sensing gas identification optimization method and system

Abstract

The application is suitable for the technical field of infrared remote gas detection and data processing optimization, and provides a multi-source infrared remote gas identification optimization method and system.The method comprises the following steps: sorting samples according to the average value of the actual conveying speed corresponding to the speed increase event in each sample from small to large, analyzing the trend of the compensation residual error optimization degree changing with the actual conveying speed based on the sample characteristic information, judging whether there is a turning interval of first rising and then falling, and adjusting the set conveying speed of the belt conveying device based on the actual conveying speed of the speed increase event of each sample in the turning interval if it is determined that there is the turning interval.The application systematically analyzes slight speed increase events naturally generated in the maintenance period of the belt conveying device, and first proposes a technical idea of using the slight speed fluctuation caused by the maintenance period to reversely optimize the infrared remote methane identification performance.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of infrared remote sensing gas detection and data processing optimization, and particularly relates to a multi-source infrared remote sensing gas identification optimization method and system. BACKGROUND

[0002] In the existing coal mine underground and other closed or semi-closed conveying environments, infrared remote sensing equipment is usually used to monitor the combustible gases such as methane in the conveying area in real time. The infrared remote sensing technology relies on the principle of infrared absorption spectrum, and through compensation of factors such as light intensity change, background absorption, and atmospheric interference, accurate gas concentration data can be obtained. However, in the actual conveying environment, due to factors such as dust raising, air disturbance, conveying material escape, light path change, and mechanical vibration, the infrared signal often fluctuates to varying degrees, resulting in the need for continuous adjustment of the compensation algorithm to maintain the identification performance. Although the existing technology has mature methods such as light path compensation, atmospheric absorption compensation, and background compensation, it still relies on the stability of the field conditions, and when facing complex conveying scenes, the compensation effect is inevitably unstable.

[0003] In the long-term operation of the belt conveying device, the conveyor will naturally and slightly fluctuate in speed due to the advancement of the maintenance cycle. Such speed changes are normal phenomena and do not affect the conveying operation, so they are often considered as insignificant equipment fluctuations in the existing technology and are not used for research on infrared monitoring performance. At the same time, the infrared compensation algorithm has a certain sensitivity to factors such as light path disturbance and speed change, but the existing monitoring system does not effectively correlate the conveyor operating state with the infrared compensation effect, nor does it systematically analyze the compensation changes caused by speed perturbations. Therefore, the existing technology cannot identify the differences in infrared compensation effect in different operating stages, and it is also unable to extract potential rules from the inherent operating data of the conveyor that can be used to improve the accuracy of infrared identification.

[0004] The current technical defects mainly lie in that the existing infrared remote sensing system relies on passive compensation methods and can only adaptively adjust after the field conditions fluctuate, but cannot predict or actively build a stable compensation optimal interval. During the advancement of the maintenance cycle, small speed increases naturally occur, which objectively affect the compensation residual, but the existing technology neither identifies the trend of this influence nor uses this trend to optimize the infrared identification performance in the opposite direction. SUMMARY

[0005] The purpose of the present application is to provide a multi-source infrared remote sensing gas identification optimization method and system to solve the problems raised in the background art.

[0006] The present application is implemented as follows: a multi-source infrared remote sensing gas identification optimization method, the method comprising:

[0007] retrieve historical working records and infrared remote monitoring records of the belt conveyor device in the infrared remote methane monitoring process;

[0008] select a plurality of samples matched with the current conveying background condition from the historical working records, and each sample has the same set conveying speed but different stages of the corresponding maintenance period;

[0009] identify a speed increase event in which the actual conveying speed is increased relative to the set conveying speed in each sample, and extract the actual conveying speed of the speed increase event;

[0010] analyze the infrared remote monitoring records, obtain compensation residual values for methane infrared identification compensation during the speed increase event and the non-speed increase event, and calculate the compensation residual optimization degree of the speed increase event relative to the non-speed increase event, perform data processing and calculation based on the actual conveying speed and the compensation residual optimization degree, and generate sample feature information for trend analysis;

[0011] sort the samples in ascending order according to the average value of the actual conveying speed corresponding to the speed increase event in each sample, analyze the trend of the compensation residual optimization degree changing with the actual conveying speed based on the sample feature information, to determine whether there is a turning interval of first rising and then falling, and if it is determined that there is, adjust the set conveying speed of the belt conveyor device based on the actual conveying speed of the speed increase event of each sample in the turning interval.

[0012] As a further limitation of the technical scheme of the embodiment of the application, the sample matched with the current conveying background condition refers to a sample in which the conveying material type is consistent and the conveying material amount is in the same order of magnitude.

[0013] As a further limitation of the technical scheme of the embodiment of the application, the different stages of the corresponding maintenance period refer to different stages within the maintenance period under the same maintenance period length and the same maintenance condition.

[0014] As a further limitation of the technical scheme of the embodiment of the application, the step of analyzing the infrared remote monitoring records, obtaining compensation residual values for methane infrared identification compensation during the speed increase event and the non-speed increase event, and calculating the compensation residual optimization degree of the speed increase event relative to the non-speed increase event, performing data processing and calculation based on the actual conveying speed and the compensation residual optimization degree, and generating sample feature information for trend analysis includes:

[0015] analyze the infrared remote monitoring records, match the time stamp of the speed increase event in each sample with the infrared remote monitoring records, and extract compensation residual values for methane infrared identification compensation during the speed increase event and the non-speed increase event;

[0016] The drop or reduction of the compensation residual value during the speed-up event relative to the compensation residual value during the non-speed-up event is calculated, and the drop or reduction is taken as a compensation residual optimization degree. Based on the actual conveying speed and the compensation residual optimization degree, data processing calculation is performed to generate sample characteristic information for trend analysis.

[0017] As a further limitation of the technical scheme of the embodiment of the present application, the compensation residual value for methane infrared identification compensation includes at least one of background compensation residual, atmospheric absorption compensation residual, or light path change compensation residual.

[0018] As a further limitation of the technical scheme of the embodiment of the present application, the samples are sorted in order from small to large according to the average value of the actual conveying speed corresponding to the speed-up event in each sample. Based on the sample characteristic information, the trend of the change of the compensation residual optimization degree with the actual conveying speed is analyzed to determine whether there is a turning interval of first rising and then falling. If it is determined that there is, the step of adjusting the set conveying speed of the belt conveying device based on the actual conveying speed of the speed-up event of each sample in the turning interval includes:

[0019] The average actual conveying speed of the actual conveying speed corresponding to all speed-up events in each sample is calculated, and each sample is sorted in order from small to large according to the average actual conveying speed to obtain a sample sequence.

[0020] The average compensation residual optimization degree of the compensation residual optimization degree corresponding to all speed-up events in each sample is calculated, and the trend of the change of the average compensation residual optimization degree with the average actual conveying speed is analyzed in the sample sequence.

[0021] It is determined whether there is a turning interval of first rising and then falling in the trend of change.

[0022] If it is determined that there is, the average value of the average actual conveying speed of each sample in the turning interval is calculated as an optimal conveying speed, and the set conveying speed of the belt conveying device is adjusted by covering the optimal conveying speed.

[0023] A multi-source infrared remote sensing gas identification optimization system, the system comprises:

[0024] A historical data calling module is configured to call historical working records and infrared remote sensing monitoring records of the belt conveying device in the process of infrared remote sensing methane monitoring.

[0025] A sample screening module is configured to screen a plurality of samples matched with the current conveying background condition from the historical working records, and each sample has the same set conveying speed but corresponds to different stages of the maintenance period.

[0026] a speed event identification module, configured to identify a speed increase event in which an actual conveying speed in each sample is increased relative to a set conveying speed, and extract the actual conveying speed of the speed increase event;

[0027] a compensation residual analysis module, configured to analyze the infrared telemetry monitoring record, obtain compensation residual values for methane infrared identification compensation during the speed increase event and during a non-speed increase event, and calculate a compensation residual optimization degree of the speed increase event relative to the non-speed increase event, perform data processing and calculation based on the actual conveying speed and the compensation residual optimization degree, and generate sample characteristic information for trend analysis;

[0028] a speed optimization decision module, configured to sort the samples from small to large according to the average value of the actual conveying speed corresponding to the speed increase event in each sample, analyze the trend of the compensation residual optimization degree changing with the actual conveying speed based on the sample characteristic information, determine whether there is a turning interval in which the compensation residual optimization degree increases first and then decreases, and if it is determined that there is a turning interval, adjust the set conveying speed of the belt conveying device based on the actual conveying speed of the speed increase event of each sample in the turning interval.

[0029] As a further limitation of the technical scheme of the embodiment of the present application, the sample matched with the current conveying background condition refers to a sample in which the conveying material type is consistent and the conveying material amount is in the same order of magnitude.

[0030] As a further limitation of the technical scheme of the embodiment of the present application, the different stages corresponding to the maintenance period refer to different stages within the maintenance period under the same maintenance period length and the same maintenance condition.

[0031] As a further limitation of the technical scheme of the embodiment of the present application, the compensation residual analysis module specifically comprises:

[0032] a compensation residual extraction unit, configured to analyze the infrared telemetry monitoring record, match the time stamp of the speed increase event in each sample with the infrared telemetry monitoring record, and extract compensation residual values for methane infrared identification compensation during the speed increase event and during a non-speed increase event;

[0033] an optimization degree calculation unit, configured to calculate a decrease amount or a reduction amplitude of the compensation residual value during the speed increase event relative to the compensation residual value during the non-speed increase event, take the decrease amount or the reduction amplitude as a compensation residual optimization degree, perform data processing and calculation based on the actual conveying speed and the compensation residual optimization degree, and generate sample characteristic information for trend analysis.

[0034] Compared with the prior art, the present application has the following beneficial effects:

[0035] The present application first proposes a technical idea of using the slight speed fluctuation caused by the maintenance cycle to reverse optimize the infrared remote methane identification performance by systematically analyzing the slight speed increase event naturally generated in the maintenance cycle of the belt conveyor. The speed perturbation is originally regarded as a random change that does not affect the operation of the equipment, but the present application reveals the objective correlation between the speed perturbation and the infrared compensation effect through sample screening, compensation residual quantization, trend modeling and other steps, and can identify the optimal speed interval corresponding to the compensation optimization peak.

[0036] Further, by reversely covering the optimal speed interval on the set conveying speed of the belt conveyor, the infrared remote system is kept in the optimal working state of compensation effect for a long time, without the need for additional hardware modification, and only relying on existing monitoring data and algorithm processing can significantly improve the identification performance. The present application effectively solves the technical problem that the prior art cannot use the inherent working condition change of the conveying system to improve the infrared identification performance, and has high adaptability, low cost and strong engineering application value. BRIEF DESCRIPTION OF DRAWINGS

[0037] Figure 1 The flowchart of the method provided by the embodiment of the present application is shown.

[0038] Figure 2 The flowchart of calculating the compensation residual optimization degree in the method provided by the embodiment of the present application is shown.

[0039] Figure 3 The flowchart of adjusting the set conveying speed in the method provided by the embodiment of the present application is shown.

[0040] Figure 4 The application architecture diagram of the system provided by the embodiment of the present application is shown.

[0041] Figure 5 The structural block diagram of the compensation residual analysis module in the system provided by the embodiment of the present application is shown. DETAILED DESCRIPTION

[0042] In order to make the purpose, technical scheme and advantages of the present application clearer and more apparent, the present application will be further described in detail below in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and do not limit the present application.

[0043] Figure 1 The flowchart of the method provided by the embodiment of the present application is shown.

[0044] Specifically, a multi-source infrared remote gas identification optimization method, the method specifically comprises the following steps:

[0045] Step S100, call the history working record of the belt conveyor device in the infrared remote methane monitoring process and the infrared remote monitoring record.

[0046] In the embodiment of the present application, the belt conveyor device can be a belt conveyor of the type of underground coal mine, roadway transportation system, coal flow concentrated conveying area, main transportation belt, transfer belt or local transportation belt inside the mining area. Such belt conveyor device is usually used for continuous conveying of coal, gangue or mixed material, and a large amount of dust and a certain amount of methane gas are released in the closed or semi-closed space during the operation. Therefore, methane gas monitoring in such conveying area is a common arrangement in the prior art, especially in the underground coal mine transportation system, infrared remote methane monitoring has become a key safety monitoring means to identify abnormal gas concentration in time and reduce safety risks.

[0047] The scenario adopted in the present application is to monitor the methane concentration in the air in the conveying area in real time by the infrared remote device during the operation of the belt conveyor device. The infrared remote device is usually arranged above the conveying belt or at the monitoring points along the conveying line, and the gas composition in the area is identified by the infrared absorption measurement method. In such a scenario, due to the dust disturbance in the conveying area, the change of air circulation, the material escape, the change of mechanical operation state and other factors, the gas identification signal obtained by the infrared remote sensing will fluctuate to different degrees, so the compensation and identification optimization of the infrared remote sensing data are the long-term technical needs in the prior art.

[0048] The history working record is used to record the running state of the belt conveyor device in each time period, which can be obtained by the belt conveyor monitoring system, equipment state recording system and coal mine safety monitoring system in the prior art. The history working record usually includes conveying speed, conveying material amount, conveying material type, equipment load, motor current, running time, maintenance cycle progress, tensioning state and other running parameters. The above data is the basic data commonly collected in the current coal mine transportation system, which is the information that can be directly recorded by mature industrial monitoring equipment.

[0049] The infrared remote monitoring record is derived from the infrared remote methane monitoring equipment deployed around the belt conveyor device. The equipment can be a fixed infrared methane monitor, a laser remote monitor or a multi-component detector based on infrared absorption spectrum. These monitoring devices will continuously output methane gas concentration information, optical path state parameters, background compensation parameters and compensation residual information generated by the internal compensation algorithm during operation. The above monitoring record is the standard output content of the existing monitoring equipment, which can be directly used as the input data for subsequent data processing.

[0050] The historical work records and the infrared remote monitoring records are automatically collected through the existing industrial monitoring system, the coal mine safety monitoring system or the gas monitoring system, and no new hardware structure needs to be additionally added, and the data sources are mature and available. Therefore, the operation of calling the two types of records is completely based on the data basis provided by the existing technology, and the further correlation analysis of the data belongs to the application optimization of the existing monitoring system.

[0051] Further, the multi-source infrared remote gas identification optimization method further includes the following steps:

[0052] Step S200, a plurality of samples matched with the current conveying background condition are screened out from the historical work records, and each sample has the same set conveying speed but different stages of the corresponding maintenance period.

[0053] The sample matched with the current conveying background condition refers to the sample with the same type of conveying material and the same order of magnitude of the conveying material amount. The different stages of the corresponding maintenance period refer to different stages within the maintenance period corresponding to the same maintenance period length and the same maintenance condition.

[0054] Step S300, a speed increase event in which the actual conveying speed is increased relative to the set conveying speed is identified in each sample, and the actual conveying speed of the speed increase event is extracted.

[0055] In the embodiment of the present application, the belt conveying device is usually periodically maintained according to the predetermined maintenance system, and the maintenance period is used to ensure that the conveying device remains stable and reliable under long-term high-load operation conditions. The maintenance period refers to the complete operation period of the belt conveying device between two routine maintenance or overhauls, and during the period, the mechanical wear of the conveying device, the relaxation of the tensioning system, the resistance of the drum and the carrier roller, the lubrication state, the motor load and the bearing state and other factors will gradually change with the running time. The setting of the maintenance period aims to ensure that the conveying system operates within a controllable wear range, so that the maintenance activities are planned, and the probability of sudden failure is reduced.

[0056] In the core research scene of the case, the belt conveyor is a typical high-load continuous operation equipment. Its conveying speed is not only a key operation control parameter, but also directly affects the conveying load, air disturbance state and background conditions of infrared remote gas detection. Generally speaking, in the early stage of the maintenance period, the mechanical resistance of the equipment is small, and the working state of each component is stable, so the conveying speed is relatively stable and does not fluctuate obviously. However, as the maintenance period progresses, the internal resistance state of the equipment, the relaxation degree of the tensioning system, the transmission friction conditions and other factors will gradually change, thereby causing an objectively existing slight speed fluctuation phenomenon. For example, at the same set conveying speed, the actual conveying speed will have a short-time increase or decrease "local event". The amplitude of such events is usually small and within the allowable range of the equipment, so it will not trigger a fault warning and will not attract special attention from the operator.

[0057] Through the analysis of a large number of infrared monitoring data in similar conveying scenes, the inventors found that a neglected but very real rule is that in the middle and later stages of the maintenance period, due to the accumulation of the above mechanical factors, the infrared remote identification end will perform better in some short-time speed increase events than in the stable operation stage. Specifically, in the short time of small amplitude speed increase, the residual error of infrared identification compensation shows a downward trend, which means that the compensation residual error optimization effect is enhanced. This shows that in some speed increase events in the period, the infrared measurement light path environment, background change smoothness or dust disturbance state is improved, so that the infrared compensation algorithm performs better. However, since this effect has amplification sensitivity, as the maintenance period further progresses, the speed increase event will first enhance the effect of compensation optimization to the peak interval, and then show a downward trend, showing the characteristics of "first increase and then decrease". After a large number of data sample verification, the speed increase amplitude corresponding to the peak interval has the most significant effect of infrared compensation optimization, so it belongs to the best area of compensation optimization.

[0058] Based on the above findings, the problem to be solved by the present application is that if the actual speed increase level corresponding to the peak interval of compensation optimization in these historical samples can be identified, and this actual speed is used as the basis for adjustment in subsequent operation, then the infrared remote gas identification effect can be kept in the relatively best interval for a long time by actively adjusting the set conveying speed within the allowed small speed range without significantly changing the overall operation speed of the conveying device.

[0059] To achieve the above-mentioned objectives, it is necessary to screen samples from historical work records in step S200. The significance of sample screening is to ensure that the data used for analysis is consistent in terms of conveying background conditions, so that there is comparability between speed improvement events. In the screening process, the sample should not only come from the same conveying material type and the same order of magnitude of the conveying material amount, but also ensure that the belt conveyor is in the same running state. The conveying background conditions include but are not limited to the conveying material type, the conveying material amount, the conveying load level, the belt conveyor running temperature, the tensioning state, the driving load parameter and other parameters that can characterize the consistency of the conveying conditions; the same running interval refers to the above-mentioned parameters being in the same or similar range, such as the material amount falling into the same order interval, the load being in the same load interval, and the temperature being in the same temperature section, so as to ensure the structured consistency of the sample.

[0060] In addition, the maintenance cycle stage of the sample does not need to belong to the same maintenance cycle, but only needs to ensure that the sample comes from different maintenance cycles but is in the same cycle length and the same internal stage of maintenance conditions, so as to be considered as the same stage type. For example, samples from the second week and the third week interval of different weeks can be included in the same stage sample as long as the maintenance conditions are consistent. The sample time length should be consistent in order to compensate for the comparability of the residual variation trend and the duration of the speed improvement event.

[0061] In step S300, it is necessary to identify the speed improvement event in the sample. The speed improvement event refers to the short-time increase of the actual conveying speed compared with the set speed in a certain period of time. In a large number of conveying system actual operation data, such events are often caused by short-time fluctuation of tensioning force, change of transmission friction coefficient, reduction of local resistance, change of load distribution or fine adjustment of motor output. The speed improvement amplitude is usually small, but its occurrence frequency is higher and the duration is longer in the later stage of the maintenance cycle. This step aims to detect and extract the event start and end time of each speed improvement event and the actual conveying speed during the whole event from the historical sample, which is used for subsequent compensation optimization trend analysis.

[0062] Further, the multi-source infrared remote sensing gas identification optimization method further comprises the following steps:

[0063] Step S400, analyzing the infrared remote sensing monitoring record, obtaining the compensation residual value for methane infrared identification compensation during the speed improvement event and the non-speed improvement event, and calculating the compensation residual optimization degree of the speed improvement event relative to the non-speed improvement event, performing data processing and calculation based on the actual conveying speed and the compensation residual optimization degree, and generating sample feature information for trend analysis.

[0064] Specifically, Figure 2 A flow chart for calculating the compensation residual optimization degree is shown.

[0065] The compensation residual value for methane infrared identification compensation during the speed promotion event and the non-speed promotion event is obtained by analyzing the infrared telemetry monitoring record, and the compensation residual optimization degree of the speed promotion event relative to the non-speed promotion event is calculated. The sample feature information for trend analysis is generated by data processing and calculation based on the actual conveying speed and the compensation residual optimization degree.

[0066] In step S401, the compensation residual value for methane infrared identification compensation during the speed promotion event and the non-speed promotion event is obtained by analyzing the infrared telemetry monitoring record, and the compensation residual optimization degree of the speed promotion event relative to the non-speed promotion event is calculated. The sample feature information for trend analysis is generated by data processing and calculation based on the actual conveying speed and the compensation residual optimization degree.

[0067] In step S401, the compensation residual value for methane infrared identification compensation during the speed promotion event and the non-speed promotion event is obtained by analyzing the infrared telemetry monitoring record, and the compensation residual optimization degree of the speed promotion event relative to the non-speed promotion event is calculated. The sample feature information for trend analysis is generated by data processing and calculation based on the actual conveying speed and the compensation residual optimization degree.

[0068] In the embodiment of the present application, step S400 is a key step for in-depth processing and analysis of infrared telemetry monitoring data. The purpose is to quantize, compare and use the numerical value of the objective law that the speed promotion event will affect the infrared identification compensation effect. By distinguishing and extracting the compensation residual values corresponding to the speed promotion event and the non-speed promotion event, calculating the difference and forming the feature data that can be processed, the infrared identification optimization effect can be expressed in a unified quantitative index, so that the trend analysis can be based on structured data.

[0069] In step S401, the compensation residual value for methane infrared identification compensation during the speed promotion event and the non-speed promotion event is obtained by analyzing the infrared telemetry monitoring record, and the compensation residual optimization degree of the speed promotion event relative to the non-speed promotion event is calculated. The sample feature information for trend analysis is generated by data processing and calculation based on the actual conveying speed and the compensation residual optimization degree.

[0070] In order to ensure the comprehensiveness and flexibility of the analysis, the compensation residual value for the methane infrared identification compensation in the present application can not only include at least one of the background compensation residual, the atmospheric absorption compensation residual or the light path change compensation residual, but also can be combined by weighting different residual values to reflect the comprehensive compensation effect. For example, a higher weight is given to the background compensation residual to highlight the influence of the background light stability; a higher weight is given to the light path change compensation residual to highlight the influence of the device vibration or dust change on the compensation effect. The comprehensive residual value generated by the weighted combination is more conducive to establishing a unified measurement system among different types of compensation algorithms.

[0071] In step S402, by calculating the amount of decrease of the compensation residual value during the speed promotion event relative to the compensation residual value during the non-speed promotion event, the improvement degree of the speed promotion event on the compensation effect can be quantified. Since the speed promotion event belongs to the slight speed fluctuation of the conveying device within the allowable range in the maintenance period, its influence on the compensation effect is manifested as different degrees of optimization, so the compensation residual decrease amount is always positive. In the middle and later stages of the maintenance period, the optimization amplitude of the speed promotion event on the compensation effect gradually increases and reaches a maximum value in a certain interval; and as the maintenance period further advances, the decrease amount will gradually decrease from the peak value interval, but still within the positive value range. In this way, by quantifying the size of the decrease amount, the present application can reflect the change trend that the compensation optimization degree first increases and then weakens in the maintenance period, thereby providing a structured analysis basis for subsequent identification of the turning interval.

[0072] Based on the actual conveying speed and the compensation residual optimization degree, the sample feature information for trend analysis is generated by data processing and calculation, which means that the actual conveying speed, speed promotion event features and corresponding compensation residual optimization degree extracted from each sample are subjected to data processing according to predetermined rules, and are structured into feature vectors that can be used for trend analysis. For example, the average actual conveying speed, speed promotion amplitude, compensation residual decrease amount and other data can be combined into a set of feature information, and the input data for trend calculation is formed by normalization, interval mapping or difference calculation. The sample feature information generated in this way can be used as the basic data for trend analysis, so that the technicians can establish the trend relationship between the speed and the compensation optimization based on these input data, thereby identifying whether there is a feature interval that first increases and then decreases.

[0073] Further, the multi-source infrared remote sensing gas identification optimization method further comprises the following steps:

[0074] Step S500, the average value of the actual conveying speed corresponding to the speed promotion event in each sample is sorted from small to large, the trend of the compensation residual error optimization degree changing with the actual conveying speed is analyzed based on the sample characteristic information, whether there is a turning interval of first rising and then falling is judged, and if it is determined that there is, the set conveying speed of the belt type conveying device is adjusted based on the actual conveying speed of the speed promotion event of each sample in the turning interval.

[0075] Specifically, Figure 3 The flowchart of modifying the set conveying speed is shown.

[0076] The average value of the actual conveying speed corresponding to the speed promotion event in each sample is sorted from small to large, the trend of the compensation residual error optimization degree changing with the actual conveying speed is analyzed based on the sample characteristic information, whether there is a turning interval of first rising and then falling is judged, and if it is determined that there is, the set conveying speed of the belt type conveying device is adjusted based on the actual conveying speed of the speed promotion event of each sample in the turning interval, and the specific steps include the following steps:

[0077] Step S501, the average actual conveying speed of the actual conveying speed corresponding to all speed promotion events in each sample is calculated, and each sample is sorted from small to large according to the average actual conveying speed, and a sample sequence is obtained;

[0078] Step S502, the average compensation residual error optimization degree of the compensation residual error optimization degree corresponding to all speed promotion events in each sample is calculated, and the change trend of the average compensation residual error optimization degree with the average actual conveying speed is analyzed in the sample sequence;

[0079] Step S503, whether there is a turning interval of first rising and then falling in the change trend is judged;

[0080] Step S504, if it is determined that there is, the average value of the average actual conveying speed of each sample in the turning interval is calculated as the optimal conveying speed, and the set conveying speed of the belt type conveying device is adjusted by the optimal conveying speed.

[0081] In the embodiment of the application, the role of step S500 is to analyze the overall trend of the sample characteristic information generated in the foregoing steps, to verify whether the infrared remote methane identification under the current conveying scene indeed has the rule that the compensation residual error optimization degree first rises and then falls with the actual conveying speed, and to identify the peak interval in the rule, that is, the turning interval with the best compensation optimization degree. Through this process, it can be further confirmed whether the core research point proposed in step S200 is established in the combination scene of the current conveying device and the conveying material, and the optimal conveying speed which can be used for actual control is obtained accordingly.

[0082] Before starting the specific calculation, it is necessary to establish the input data of trend analysis based on sample characteristic information. The sample characteristic information includes the average actual conveying speed of each sample in its historical sequence of speed promotion events, the average value of the compensation residual optimization degree, and other trend-related statistical characteristics generated by the data processing step. The sample characteristic information provides the basis data for trend analysis, enabling the compensation residual optimization degree to be used as the dependent variable and the average actual conveying speed as the independent variable to form a data mapping relationship that can be modeled for trends. By reading the structured sample characteristic information, the change direction, change amplitude, change interval, and whether there is a peak value of the compensation optimization degree at different speed levels can be observed, thereby serving as the basis for subsequent calculations.

[0083] In step S501, the speed promotion events of each sample need to be summarized, and the actual conveying speeds of all speed promotion events within the same sample are averaged to obtain the average actual conveying speed of the sample. Since the maintenance period phase, the number of speed promotion events, and the event duration of the sample may be different, directly comparing the speed values of the events cannot reflect the overall speed level of the sample. By averaging, the disturbance of a single event on the trend can be avoided. Then, all samples are sorted in ascending order of average actual conveying speed to obtain the sample sequence for trend analysis. The sorting process can use direct sorting algorithms, stable sorting methods, or interval sorting methods based on numerical intervals, all of which are common data processing means in the prior art.

[0084] In step S502, the average value of the compensation residual optimization degree corresponding to all speed promotion events in each sample needs to be calculated to form the compensation optimization characteristics for trend analysis. In the sample sequence, the average compensation residual optimization degree is matched with the average actual conveying speed, and by analyzing the trend of the compensation residual optimization degree with the average actual conveying speed, it is identified whether there is an enhancement interval, a peak interval, and a decline interval of the compensation optimization. Trend analysis can use difference analysis methods, data fitting methods, local monotonicity identification methods, moving average methods, or interval change rate analysis methods. Through the above analysis, the change of the compensation optimization degree at different speed levels can be observed directly, and the compensation optimization law can be reflected at the data level.

[0085] In step S503, it is necessary to determine whether there is a turning interval of first rising and then falling. By observing the change direction of the average compensation residual error optimization degree in the sample sequence, when the optimization degree gradually increases with the increase of the speed and reaches a peak and then decreases, it can be considered that there is a compensation optimization peak interval. The judgment can be made by means of maximum value point identification, derivative sign change analysis or interval change rate reversal detection, which all belong to mature data processing methods. Considering that the infrared compensation process has high sensitivity and amplification to light path disturbance, dust change and speed disturbance, in some scenes, multiple local inverted U-shaped change regions with the characteristics of first rising and then falling may be formed. In this case, the inverted U-shaped region with the largest change amplitude and the most obvious peak value can be selected as the target turning interval to ensure that the determined interval can reflect the strongest compensation optimization effect. Identifying the turning interval is crucial to the present application, because the interval represents the strongest compensation optimization effect brought by the speed increase event, and also indicates that the infrared identification system is most sensitive to speed disturbance and the compensation is most sufficient in this speed region.

[0086] In step S504, the average value of the average actual conveying speed of each sample in the turning interval needs to be calculated, and the average speed is taken as the optimal conveying speed. The selection of the optimal conveying speed is fully reasonable. On the one hand, the speed belongs to the speed floating range that the belt conveyor can naturally reach in the maintenance period, and will not cause additional burden to the conveying equipment or trigger a warning; on the other hand, the speed corresponds to the peak interval of the compensation residual error optimization degree, so that the infrared remote methane identification compensation algorithm is in a relatively optimal performance zone for a long time, thereby improving the monitoring data stability and identification accuracy. In addition, by using the optimal conveying speed to cover and adjust the set conveying speed, the conveying device can be maintained in a state close to the best light path stability and dust disturbance minimization throughout the running period, further improving the overall performance of the infrared remote system.

[0087] The overall beneficial effect of the present application is that by systematically collecting, structuring and trend analyzing the small speed changes naturally generated by the conveying device in the maintenance period, the speed characteristics that can be used to optimize the infrared identification performance in the opposite direction are extracted from the historical data, so that the infrared compensation effect can be kept in the optimal amplitude range for a long time. The present application does not need to change the existing infrared monitoring device, nor does it need to increase additional hardware cost, but only by algorithm processing of the existing monitoring records and conveying data, the infrared identification optimization capability can be obtained. The scheme effectively solves the technical problem that the natural working condition changes cannot be fully utilized to improve the infrared monitoring performance in the prior art, and realizes the cooperative optimization between the conveying device running state and the infrared compensation algorithm.

[0088] The application has strong application prospects, and is especially suitable for coal mine underground, roadway conveying system, centralized transportation system and other scenes requiring long-term stable monitoring of harmful gases such as methane. With the development of intelligent construction of mines, the application can be quickly deployed as a monitoring optimization method based on data driving without hardware investment, is suitable for large-scale coal mine conveying system, and realizes the improvement of overall safety monitoring performance. Meanwhile, the idea of the application can also be applied to other industrial monitoring scenes based on infrared detection, and has high engineering application value and popularization potential.

[0089] Further, Figure 4 The application architecture diagram of the system provided by the embodiment of the application is shown.

[0090] In a preferred embodiment of the application, a multi-source infrared remote sensing gas identification optimization system comprises:

[0091] The historical data calling module 100 is configured to call historical working records and infrared remote sensing monitoring records of the belt conveying device in the infrared remote sensing methane monitoring process.

[0092] Further, the multi-source infrared remote sensing gas identification optimization system further comprises:

[0093] The sample screening module 200 is configured to screen a plurality of samples matched with the current conveying background condition from the historical working records, and each sample has the same set conveying speed but different stages of the corresponding maintenance period.

[0094] The sample matched with the current conveying background condition refers to a sample with consistent conveying material type and conveying material amount in the same order of magnitude. The different stages of the corresponding maintenance period refer to different stages within the maintenance period under the same maintenance period length and the same maintenance condition.

[0095] Further, the multi-source infrared remote sensing gas identification optimization system further comprises:

[0096] The speed event identification module 300 is configured to identify a speed increase event in which the actual conveying speed in each sample is increased relative to the set conveying speed, and extract the actual conveying speed of the speed increase event.

[0097] Further, the multi-source infrared remote sensing gas identification optimization system further comprises:

[0098] The compensation residual analysis module 400 is configured to analyze the infrared remote monitoring record, obtain compensation residual values for methane infrared identification compensation during the speed increasing event and during the non-speed increasing event, and calculate a compensation residual optimization degree of the speed increasing event relative to the non-speed increasing event. Based on the actual conveying speed and the compensation residual optimization degree, data processing and calculation are performed to generate sample characteristic information for trend analysis.

[0099] Specifically, Figure 5 A structural block diagram of the compensation residual analysis module 400 in the system provided by the embodiment of the present application is shown.

[0100] In the preferred embodiment provided by the present application, the compensation residual analysis module 400 specifically includes:

[0101] The compensation residual extraction unit 401 is configured to analyze the infrared remote monitoring record, match the time stamp of the speed increasing event in each sample with the infrared remote monitoring record, and extract compensation residual values for methane infrared identification compensation during the speed increasing event and during the non-speed increasing event.

[0102] The optimization degree calculation unit 402 is configured to calculate a drop amount or a reduction amplitude of the compensation residual value during the speed increasing event relative to the compensation residual value during the non-speed increasing event, and take the drop amount or the reduction amplitude as a compensation residual optimization degree. Based on the actual conveying speed and the compensation residual optimization degree, data processing and calculation are performed to generate sample characteristic information for trend analysis.

[0103] Further, the multi-source infrared remote gas identification optimization system further includes:

[0104] The speed optimization decision module 500 is configured to sort the samples from small to large according to the average value of the actual conveying speed corresponding to the speed increasing event in each sample, analyze a trend of the compensation residual optimization degree changing with the actual conveying speed based on the sample characteristic information, determine whether there is a turning interval of first rising and then falling, and adjust the set conveying speed of the belt conveying device based on the actual conveying speed of the speed increasing event of each sample in the turning interval if it is determined that there is the turning interval.

[0105] It should be understood that, although the steps in the flowcharts of the embodiments of the present application are shown in a certain order according to the arrows, the steps are not necessarily executed in the order of the arrows. Unless otherwise specified herein, the execution of the steps is not strictly limited in order, and the steps can be executed in other orders. Moreover, at least some of the steps in the embodiments can include a plurality of sub-steps or a plurality of stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution order of the sub-steps or stages is not necessarily sequential, but can be round-robin or alternately executed with at least some of the other steps or sub-steps or stages of the other steps.

[0106] It can be understood by those skilled in the art that all or part of the processes in the above-mentioned embodiments can be completed by a computer program instructing related hardware, and the program can be stored in a non-volatile computer readable storage medium. When the program is executed, it can include the processes of the above-mentioned embodiments of the methods. Any reference to memory, storage, database or other medium used in the embodiments provided in the present application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration but not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0107] The technical features of the above-mentioned embodiments can be combined in any way. In order to make the description concise, all possible combinations of the technical features in the above-mentioned embodiments are not described, but as long as the combination of the technical features does not exist, it should be considered as the scope of the present application.

[0108] The above embodiments only express several implementation manners of the present application, which are described in a more specific and detailed manner, but should not be understood as a limitation on the patent scope of the present application. It should be noted that, for ordinary skilled persons in the art, several modifications and improvements can be made without departing from the concept of the present application, which are all within the protection scope of the present application. Therefore, the protection scope of the patent of the present application should be subject to the appended claims.

[0109] The above merely describes the preferred embodiments of the present application and should not be used to limit the present application. Any modification, equivalent replacement and improvement made within the spirit and principle of the present application should be included in the protection scope of the present application.

Claims

1. An optimized method for gas identification using multi-source infrared remote sensing, characterized in that, The method includes: Retrieve historical work records and infrared telemetry monitoring records of the belt conveyor during the infrared remote sensing methane monitoring process; Several samples matching the current transport background conditions are selected from historical work records. Each sample has the same set transport speed, but the corresponding maintenance cycle is at a different stage. Identify speed increase events in each sample where the actual conveying speed increases relative to the set conveying speed, and extract the actual conveying speed of the speed increase event; The infrared telemetry monitoring records are analyzed to obtain the compensation residual values ​​for methane infrared identification compensation during and before speed increase events. The degree of optimization of the compensation residual during speed increase events relative to the degree of optimization of the compensation residual is calculated. Based on the actual delivery speed and the degree of optimization of the compensation residual, data processing calculations are performed to generate sample feature information for trend analysis. The samples are sorted from smallest to largest based on the average actual conveying speed corresponding to the speed increase event in each sample. The trend of the degree of compensation residual optimization with the actual conveying speed is analyzed based on the sample feature information to determine whether there is a turning point interval of first rising and then falling. If it is determined to exist, the set conveying speed of the belt conveyor is adjusted based on the actual conveying speed of the speed increase event of each sample in the turning point interval.

2. The multi-source infrared remote sensing gas identification optimization method according to claim 1, characterized in that, The sample that matches the current transport background conditions refers to a sample that is transporting the same type of material and the amount of material being transported is at the same level.

3. The multi-source infrared remote sensing gas identification optimization method according to claim 1, characterized in that, The different stages of the corresponding maintenance cycle refer to the fact that each sample corresponds to a different stage within the same maintenance cycle under the same maintenance cycle length and maintenance conditions.

4. The multi-source infrared remote sensing gas identification optimization method according to claim 1, characterized in that, The steps of analyzing infrared telemetry monitoring records to obtain compensation residual values ​​for methane infrared identification compensation during and outside of speed-increase events, calculating the degree of optimization of compensation residuals during speed-increase events relative to those during non-speed-increase events, and generating sample feature information for trend analysis based on actual transport speed and the degree of optimization of compensation residuals include: Analyze the infrared telemetry monitoring records, match the timestamps of velocity increase events in each sample with the corresponding infrared telemetry monitoring records, and extract the compensation residual values ​​used for methane infrared identification compensation during the velocity increase event period and the non-velocity increase event period. The calculation involves the decrease or reduction in the compensation residual value during the speed increase event relative to the compensation residual value during the non-speed increase event, and the decrease or reduction is used as the degree of optimization of the compensation residual. Based on the actual conveying speed and the degree of optimization of the compensation residual, data processing calculations are performed to generate sample feature information for trend analysis.

5. The multi-source infrared remote sensing gas identification optimization method according to claim 4, characterized in that, The compensation residual value used for methane infrared recognition compensation includes at least one of background compensation residual, atmospheric absorption compensation residual, or optical path change compensation residual.

6. The multi-source infrared remote sensing gas identification optimization method according to claim 4, characterized in that, The samples are sorted from smallest to largest according to the average actual conveying speed corresponding to the speed increase events in each sample. Based on the sample feature information, the trend of the degree of compensation residual optimization with the change of actual conveying speed is analyzed to determine whether there is a turning point interval of first rising and then falling. If it is determined to exist, the steps to adjust the set conveying speed of the belt conveyor based on the actual conveying speed of the speed increase events of each sample within the turning point interval include: Calculate the average actual transport speed corresponding to all speed increase events in each sample, and sort the samples in ascending order of average actual transport speed to obtain the sample sequence; Calculate the average compensation residual optimization degree corresponding to all speed increase events in each sample, and analyze the trend of the average compensation residual optimization degree with the average actual conveying speed in the sample sequence; Determine whether there is a turning point in the trend of change where the price first rises and then falls; If it is determined that it exists, the average of the average actual conveying speed of each sample within the transition interval is calculated as the optimal conveying speed, and the optimal conveying speed is used to cover the set conveying speed of the belt conveyor.

7. A multi-source infrared remote sensing gas identification optimization system, characterized in that, The system includes: The historical data retrieval module is used to retrieve historical work records and infrared remote sensing monitoring records of the belt conveyor during the infrared remote sensing methane monitoring process. The sample screening module is used to select several samples from historical work records that match the current transport background conditions. Each sample has the same set transport speed, but the corresponding maintenance cycle is at a different stage. The speed event recognition module is used to identify speed increase events in each sample where the actual conveying speed increases relative to the set conveying speed, and to extract the actual conveying speed of the speed increase event. The compensation residual analysis module is used to parse infrared telemetry monitoring records, obtain compensation residual values ​​for methane infrared identification compensation during and before speed increase events, calculate the degree of compensation residual optimization for speed increase events relative to non-speed increase events, perform data processing calculations based on actual transport speed and the degree of compensation residual optimization, and generate sample feature information for trend analysis. The speed optimization decision module sorts the samples from smallest to largest according to the average actual conveying speed corresponding to the speed increase event in each sample. Based on the sample feature information, it analyzes the trend of the degree of compensation residual optimization with the change of actual conveying speed to determine whether there is a turning point interval of first rising and then falling. If it is determined to exist, the set conveying speed of the belt conveyor is adjusted based on the actual conveying speed of the speed increase event of each sample in the turning point interval.

8. The multi-source infrared remote sensing gas identification optimization system according to claim 7, characterized in that, The sample that matches the current transport background conditions refers to a sample that is transporting the same type of material and the amount of material being transported is at the same level.

9. The multi-source infrared remote sensing gas identification optimization system according to claim 8, characterized in that, The different stages of the corresponding maintenance cycle refer to the fact that each sample corresponds to a different stage within the same maintenance cycle under the same maintenance cycle length and maintenance conditions.

10. The multi-source infrared remote sensing gas identification optimization system according to claim 9, characterized in that, The compensation residual analysis module specifically includes: The compensation residual extraction unit is used to parse the infrared telemetry monitoring records, match the timestamps of velocity increase events in each sample with the corresponding infrared telemetry monitoring records, and extract the compensation residual values ​​used for methane infrared identification compensation during the velocity increase event period and the non-velocity increase event period. The optimization degree calculation unit is used to calculate the decrease or reduction magnitude of the compensation residual value during the speed increase event relative to the compensation residual value during the non-speed increase event, and uses the decrease or reduction magnitude as the optimization degree of the compensation residual. Based on the actual conveying speed and the optimization degree of the compensation residual, data processing calculation is performed to generate sample feature information for trend analysis.

Images