Coal heat index remote intelligent detection method based on wireless calorimeter

Abstract

The invention relates to the technical field of coal heat detection, and discloses a coal heat index remote intelligent detection method based on a wireless calorimeter. Comprising the following steps: establishing a plurality of coal heat detection points according to plant equipment parameters; acquiring to-be-measured coal sample parameters, and generating a coal sample heat prediction result according to a preset heat prediction model and the to-be-measured coal sample parameters; generating a matching evaluation value of the coal sample to be detected and each coal heat detection point, setting primary detection points according to all the matching evaluation values, and selecting secondary detection points from the primary detection points according to the detection waiting time; acquiring a coal sample heat detection result of the to-be-detected coal sample at the secondary detection point, and judging whether a correction instruction is generated or not according to the coal sample heat detection result and the coal sample heat prediction result; and generating an abnormal risk value of each coal heat detection point according to a preset evaluation time node, and judging whether a maintenance instruction is generated or not according to all the abnormal risk values. And suitable detection points are selected for detection based on the comprehensive evaluation degree, so that the detection efficiency and accuracy are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of coal calorific value detection, and particularly to a remote intelligent detection method for coal calorific value indicators based on a wireless calorimeter. Background Technique

[0002] The calorific value of coal is an important indicator for coal classification and coal quality analysis, and is also the basis for thermal engineering calculations. During the combustion or conversion process of coal, calorific value is commonly used for heat balance, thermal efficiency, and coal consumption calculations, and based on this, equipment selection or combustion mode selection is carried out. By detecting the calorific value, the energy value of coal can be accurately evaluated, providing a scientific basis for the pricing, trading, and use of coal.

[0003] Thermal power generation is one of the main application fields of coal. Accurate coal calorific value detection can help power plants optimize their coal procurement strategies, rationally allocate coal resources, and ensure boiler combustion efficiency and power generation efficiency.

[0004] Most traditional coal calorific value detection methods use an oxygen bomb calorimeter for detection. The detection process requires manual sample preparation and data processing, which has problems such as cumbersome operation, long time consumption, inability to achieve remote monitoring, lack of remote monitoring and intelligent analysis capabilities, and the detection process is affected by various factors, easily generating errors, and it is difficult to meet the requirements of modern coal mine intelligent management. Summary of the Invention

[0005] The purpose of the present invention is: to solve the above technical problems, the present application provides a remote intelligent detection method for coal calorific value indicators based on a wireless calorimeter, aiming to achieve real-time data transmission between the calorimeter and the remote monitoring terminal through wireless technology, and combine intelligent algorithms to analyze and process the detection data to improve the detection efficiency and accuracy.

[0006] In some embodiments of the present application, multiple coal calorific value detection points are set up, a matching evaluation value between the coal sample to be tested and each coal calorific value detection point is generated, a primary detection point is set according to all the matching evaluation values, a secondary detection point is selected from the primary detection points according to the detection waiting time, and the coal sample to be tested is subjected to calorific value detection through the secondary detection point, which not only improves the detection accuracy but also improves the detection efficiency and shortens the sample waiting time.

[0007] In some embodiments of the present application, it is judged whether to generate a correction instruction according to the coal sample calorific value detection result and the coal sample calorific value prediction result, and the coal sample calorific value detection result is verified once according to the effectiveness of the coal sample calorific value detection process; the coal sample calorific value detection result is verified twice according to the credibility of the coal sample calorific value detection result; after both verifications pass, the coal sample calorific value detection result is uploaded to the remote central control terminal, otherwise a correction instruction is generated and the coal sample calorific value detection result is obtained again. This further ensures the effectiveness of the detection and greatly enhances the reliability and accuracy of the detection result.

[0008] In some embodiments of the present application, by generating the abnormal risk value of each detection point and performing hierarchical maintenance according to the abnormal risk value, not only can the failure rate of the detection point be effectively reduced, the service life of the equipment be extended, but also the maintenance cost and downtime be reduced, and the stability of the system be improved.

[0009] In some embodiments of the present application, a remote intelligent detection method for coal calorific value indicators based on a wireless calorimeter is provided, including: Establish multiple coal calorific value detection points according to the plant equipment parameters; Obtain the parameters of the coal sample to be tested, and generate the predicted coal sample calorific value result according to the preset calorific value prediction model and the parameters of the coal sample to be tested; Generate the matching evaluation value between the coal sample to be tested and each coal calorific value detection point, set the first-level detection points according to all the matching evaluation values, and select the second-level detection points from the first-level detection points according to the detection waiting time; Obtain the coal sample calorific value detection result of the coal sample to be tested at the second-level detection point, and judge whether to generate a correction instruction according to the coal sample calorific value detection result and the predicted coal sample calorific value result; Generate the abnormal risk value of each coal calorific value detection point according to the preset evaluation time node, and judge whether to generate a maintenance instruction according to all the abnormal risk values; Among them, when setting up multiple coal calorific value detection points, it includes: Establish a sequence A of coal calorific value detection points, A=(a 1 ,a 2 …a i …a n ), where a i is the i-th coal calorific value detection point; n is the number of coal calorific value detection points.

[0010] In some embodiments of the present application, the generation of the matching evaluation value between the coal sample to be tested and each coal calorific value detection point includes: Sequentially select a i from the sequence A of coal calorific value detection points as the target coal calorific value detection point; Generate the matching evaluation value λ i between the coal sample to be tested and the i-th coal calorific value detection point a i ; λ i = ; Among them, m is the number of matching degree evaluation indicators, is the preset weight coefficient of the i-th matching degree evaluation indicator, is the reference value of the i-th matching degree evaluation indicator of the coal sample to be tested, is the reference value of the i-th coal calorific value detection point in the i-th matching degree evaluation indicator; The matching evaluation values ​​of the coal sample to be tested and other coal heat detection points are generated in sequence.

[0011] In some embodiments of the present application, the step of setting the primary detection point according to all matching evaluation values ​​includes: Preset a first matching evaluation value threshold λ'; According to the coal heat detection point number column A, select a i It is the target coal heat detection point; Determine whether to set the i-th coal heat detection point as a primary detection point; When i >λ', the ith coal heat detection point is set as the first-level detection point; It is determined in turn whether to set other coal heat detection points as primary detection points; Establish a first-level detection point sequence, A 1 ,A 1 =( , … … ), where a i is the i-th first-level detection point; n 1 is the number of first-level detection points, n 1 n; In some embodiments of the present application, the step of selecting a secondary detection point from the primary detection points according to the detection waiting time includes: According to the number of primary detection points, A 1 Select the i-th first-level detection point in turn It is the target first-level detection point; Generate first-level detection points The relative waiting time coefficient t i ; According to the first-level detection point Matching evaluation value and primary detection point with the coal sample to be tested The relative waiting time coefficient of the first-level detection point is obtained The comprehensive evaluation value W i ; W i =Q 1 *P 1 * +Q 2 *P 2 *β i ; Among them, Q 1 is the preset first fixed coefficient, Q 2 To preset the second fixed coefficient, P 1 is the preset first weight coefficient, P2 is a preset second weight coefficient, is the i-th primary detection point and the matching evaluation value of the coal sample to be measured, β i is the primary detection point of the relative waiting time coefficient; Calculate the comprehensive evaluation values of the coal sample to be measured and other primary detection points in sequence; Select the primary detection point sequence A 1 The primary detection point with the highest comprehensive evaluation value in is the secondary detection point.

[0012] In some embodiments of the present application, the generating of the relative waiting time coefficient of the primary detection point includes: According to the primary detection point sequence A 1 Select in sequence as the target primary detection point; Calculate the detection waiting time t required for the coal sample to be measured to be sent to the target primary detection point for detection i , t i = max( , ), where is the time consumed on the way from the position of the coal sample to be measured to the position of the target primary detection point, is the time required for the target primary detection point to complete the current task; Calculate the detection waiting time required for the coal sample to be measured to be sent to other primary detection points for detection; Generate the detection waiting time sequence T required for the coal sample to be measured to be detected by the coal calorific value detection point, T = (t 1 , t 2 … t i … t n1 ), where t i is the detection waiting time required for the coal sample to be measured to be sent to the i-th primary detection point for detection; n 1 is the number of primary detection points; Generate the relative waiting time coefficient β of the i-th primary detection point according to the detection waiting time sequence T i ; ; where, β i has a value range of (0, 1), t min is the minimum value in the sequence T, t max is the maximum value in the sequence T.

[0013] In some embodiments of the present application, the judging whether to generate a correction instruction according to the coal sample calorific value detection result and the coal sample calorific value prediction result includes: Verify the calorific value detection result of the coal sample once according to the effectiveness of the coal sample calorific value detection process; Verify the calorific value detection result of the coal sample twice according to the credibility of the coal sample calorific value detection result; If one of the two verifications fails, generate a correction instruction.

[0014] In some embodiments of the present application, the first verification of the calorific value detection result of the coal sample according to the effectiveness of the coal sample calorific value detection process includes: Preset the first effectiveness threshold y 1 ; Calculate the effectiveness y of the coal sample calorific value detection process; y = *u i ; where k is the number of evaluation indicators for the coal sample calorific value detection process, is the preset weight coefficient of the i-th evaluation indicator, u i is the evaluation value of the i-th evaluation indicator; Conduct the first verification on the calorific value detection result of the coal sample; When y < y 1 , the first verification fails, and a correction instruction is generated; When y y 1 , the first verification passes, and the second verification of the calorific value detection result of the coal sample is conducted.

[0015] In some embodiments of the present application, the second verification of the calorific value detection result of the coal sample according to the credibility of the coal sample calorific value detection result includes: Preset the first credibility threshold g 1 ; Calculate the fitting degree z between the calorific value detection result of the coal sample and the calorific value prediction result of the coal sample; ; where is the calorific value prediction result of the coal sample, is the calorific value detection result of the coal sample; Calculate the credibility g of the calorific value detection result of the coal sample according to the effectiveness of the coal sample calorific value detection process and the fitting degree between the calorific value detection result of the coal sample and the calorific value prediction result of the coal sample; g = Q 3 *P 3 *y + Q 4 *P 4 *z; where Q 3 is the preset third fixed coefficient, Q 4 is the preset fourth fixed coefficient, P 3 is the preset third weight coefficient, P4 Let \(x\) be the preset fourth weight coefficient, \(y\) be the effectiveness of the coal sample heat detection process, and \(z\) be the degree of fit between the coal sample heat detection result and the coal sample heat prediction result; When \(g \lt g\) 1 the secondary verification fails, and a correction instruction is generated; When \(g\) \(g\) 1 the secondary verification passes, and the coal sample heat detection result is uploaded to the remote central control terminal.

[0016] In some embodiments of the present application, the correction instruction includes: re-perform heat detection on the coal sample to be tested; generate the comprehensive evaluation values of the coal sample to be tested and each primary detection point in the primary detection point sequence \(A\) 1 ; remove the comprehensive evaluation value corresponding to the primary detection point that was selected as the secondary detection point last time, and sort the remaining comprehensive evaluation values in descending order; select the primary detection points with the top \(L\) comprehensive evaluation values to perform detection on the coal sample to be tested, and obtain \(L\) groups of coal sample heat detection results; generate the coal sample heat detection result sequence \(C\), \(C=(c\) 1 , \(c\) 2 … \(c\) i … \(c\) L ), where \(c\) i is the \(i\)-th group of coal sample heat detection results; \(L\) is the number of coal sample heat detection groups; preset the second effectiveness threshold \(y\) 2 , and screen the coal sample heat detection result sequence \(C\), and select the coal sample heat detection results with the effectiveness of the coal sample heat detection process greater than \(y\) 2 ; establish the screened coal sample heat detection result sequence \(C\) 1 , \(C\) 1 =( , … … ), is the \(i\)-th group of screened coal sample heat detection results, \(L1\) is the number of screened coal sample heat detection groups, \(L1\) \(\leq L\); calculate the coal sample heat detection result \(c'\) according to the screened coal sample heat detection result sequence \(C\) 1 ; ; upload the coal sample heat detection result \(c'\) to the remote central control terminal.

[0017] In some embodiments of the present application, judging whether to generate a maintenance instruction according to all abnormal risk values includes: Preset the first abnormal risk value threshold X 1 and the second abnormal risk value threshold X 2 , and X 1 < X 2 ; Select a i from the coal calorific value detection point sequence A in turn as the target coal calorific value detection point; Generate the abnormal risk value x i of the i-th coal calorific value detection point a at the current evaluation time node i ; x i = Q 5 * P 5 * + Q 6 * P 6 * + Q 7 * P 7 * ( - ) * H(i) where Q 5 is the preset fifth fixed coefficient, Q 6 is the preset sixth fixed coefficient, Q 7 is the preset seventh fixed coefficient, P 5 is the preset fifth weight coefficient, P 6 is the preset sixth weight coefficient, P 7 is the preset seventh weight coefficient, is the total number of first verification failures of the i-th coal calorific value detection point since the last maintenance, is the total number of second verification failures of the i-th coal calorific value detection point since the last maintenance, is the time of the i-th coal calorific value detection point since the last maintenance, is the preset standard maintenance time, H(i) is the selection coefficient, when ( - ) > 0, H(i) = 1, otherwise H(i) = 0; When x i < X 1 , the i-th coal calorific value detection point a i does not generate a maintenance instruction; When X 1 x i < X 2 , the i-th coal calorific value detection point a i generates a first-level maintenance instruction; When X 1 x i , for the i-th coal calorific value detection point a iGenerate secondary maintenance instructions; Sequentially generate the abnormal risk values of each coal calorific value detection point at the current evaluation time node, and determine whether to generate maintenance instructions based on the abnormal risk values.

[0018] Compared with the prior art, the beneficial effects of a remote intelligent detection method for coal calorific value indicators based on a wireless calorimeter according to an embodiment of the present application are as follows: The present application sets up multiple coal calorific value detection points, generates matching evaluation values between the coal samples to be measured and each coal calorific value detection point, sets the primary detection points according to all the matching evaluation values, selects the secondary detection points from the primary detection points according to the detection waiting time, and performs calorific value detection on the coal samples to be measured through the secondary detection points. This can not only improve the detection accuracy, but also improve the detection efficiency and shorten the sample waiting time.

[0019] The present application determines whether to generate a correction instruction based on the coal sample calorific value detection result and the coal sample calorific value prediction result, and performs a primary verification on the coal sample calorific value detection result according to the effectiveness of the coal sample calorific value detection process; performs a secondary verification on the coal sample calorific value detection result according to the credibility of the coal sample calorific value detection result; after both verifications are passed, upload the coal sample calorific value detection result to the remote central control terminal, otherwise generate a correction instruction and obtain the coal sample calorific value detection result again. This further ensures the effectiveness of the detection and greatly enhances the reliability and accuracy of the detection result.

[0020] By generating the abnormal risk value of each detection point and performing hierarchical maintenance according to the abnormal risk value, the present application can not only effectively reduce the failure rate of the detection point, extend the service life of the equipment, but also reduce the maintenance cost and downtime, and improve the stability of the system. Brief Description of the Drawings

[0021] Figure 1 is a schematic flowchart of a remote intelligent detection method for coal calorific value indicators based on a wireless calorimeter according to an embodiment of the application. Detailed Description of the Embodiment

[0022] The following combines the drawings and embodiments to further describe in detail the specific implementation manners of the present invention. The following embodiments are used to illustrate the present invention, but are not used to limit the scope of the present invention.

[0023] In the description of the present application, it should be understood that the orientation or positional relationship indicated by the terms "center", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. is based on the orientation or positional relationship shown in the drawings, and is only for the convenience of describing the present application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation to the present application.

[0024] The terms "first" and "second" are for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of this application, unless otherwise specified, the meaning of "a plurality" is two or more.

[0025] In the description of this application, it should be noted that, unless otherwise clearly specified and defined, the terms "installed", "connected", and "coupled" should be understood in a broad sense. For example, it may be a fixed connection, a detachable connection, or an integral connection; it may be a mechanical connection or an electrical connection; it may be directly connected or indirectly connected through an intermediate medium, and it may be the communication inside two components. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0026] As Figure 1 shown, a remote intelligent detection method for coal calorific value indicators based on a wireless calorimeter in a preferred embodiment of an embodiment of the present invention includes: S100: Establish a plurality of coal calorific value detection points according to the plant equipment parameters; S200: Obtain the parameters of the coal sample to be measured, and generate a coal sample calorific value prediction result according to a preset calorific value prediction model and the parameters of the coal sample to be measured; S300: Generate a matching evaluation value between the coal sample to be measured and each coal calorific value detection point, set a first-level detection point according to all the matching evaluation values, and select a second-level detection point from the first-level detection points according to the detection waiting time; S400: Obtain the coal sample calorific value detection result of the coal sample to be measured at the second-level detection point, and determine whether to generate a correction instruction according to the coal sample calorific value detection result and the coal sample calorific value prediction result; S500: Generate an abnormal risk value for each coal calorific value detection point according to a preset evaluation time node, and determine whether to generate a maintenance instruction according to all the abnormal risk values; Among them, when setting a plurality of coal calorific value detection points, it includes: Establish a sequence A of coal calorific value detection points, A = (a 1 , a 2 … a i … a n ), where a i is the i-th coal calorific value detection point; n is the number of coal calorific value detection points.

[0027] Specifically, the wireless calorimeter is a constant-temperature automatic calorimeter with a wireless communication module. After the coal sample to be measured is detected by the wireless calorimeter, the calorific value detection result is uploaded to the remote central control terminal through the wireless communication module.

[0028] Specifically, the preset calorific value prediction model is a mathematical model that predicts the calorific value of coal by analyzing its physical and chemical properties. The establishment process includes the following steps: collecting a large amount of coal sample data, which should include the calorific value of coal (as the target variable) and related physical and chemical properties (as input variables); preprocessing the data and importing the preprocessed data into a suitable mathematical model (such as a multiple linear regression model); training and validating the model.

[0029] Specifically, the physical and chemical properties of coal should include: total moisture, ash, volatile matter, fixed carbon content, etc.

[0030] Specifically, generating the matching evaluation value between the coal sample to be measured and each coal calorific value detection point includes: Sequentially select a i as the target coal calorific value detection point according to the coal calorific value detection point sequence A; Generate the matching evaluation value λ i between the coal sample to be measured and the i-th coal calorific value detection point a i ; λ i = ; where m is the number of matching degree evaluation indicators, is the preset weight coefficient of the i-th matching degree evaluation indicator, is the reference value of the i-th matching degree evaluation indicator of the coal sample to be measured, is the reference value of the i-th coal calorific value detection point in the i-th matching degree evaluation indicator; Sequentially generate the matching evaluation values between the coal sample to be measured and other coal calorific value detection points.

[0031] Specifically, the matching degree evaluation indicators include ash, volatile matter, etc. Different detection processes should be adopted for high-ash coal samples and high-volatile coal samples compared with general coal quality coal samples. Generate the matching evaluation value between the coal sample to be measured and each coal calorific value detection point according to the parameters of the coal sample to be measured. The higher the matching evaluation value, the more accurate the calorific value detection result.

[0032] For coal samples of general coal quality, they are determined according to GB / T 213—2008 "Methods for the Determination of Calorific Value of Coal", and the determination results are basically close to the true value. For high-ash and high-volatile coals, problems such as difficult combustion and splashing will occur during the calorific value determination process, and the determination results will deviate from the true value, and the error of the repeatability test is likely to exceed the requirements specified in GB / T 213—2008. The measurement process needs to be adjusted specifically.

[0033] The calorific value detection method for general coal quality coal samples is carried out in accordance with GB / T 213—2008 "Method for Determination of Calorific Value of Coal". In the calorific value detection process of high-ash coal samples, asbestos wool is required as a gasket and lens paper is used to wrap the coal samples during the detection process. In the calorific value detection process of high-volatile coal samples, the mass of the coal samples to be detected needs to be reduced. In the calorific value detection process of high-volatile and high-ash coal samples, both the mass of the coal samples to be detected needs to be reduced, and asbestos wool is required as a gasket and lens paper is used to wrap the coal samples.

[0034] Specifically, the setting of the first-level detection points according to all matching evaluation values includes: Presetting the first matching evaluation value threshold λ'; Sequentially select a i from the coal calorific value detection point sequence A as the target coal calorific value detection point; Judge whether to set the i-th coal calorific value detection point as a first-level detection point; When λ i >λ', set the i-th coal calorific value detection point as a first-level detection point; Sequentially judge whether to set other coal calorific value detection points as first-level detection points; Establish a first-level detection point sequence, A 1 ,A 1 =( , … … ), where a i is the i-th first-level detection point; n 1 is the number of first-level detection points, n 1 n; Specifically, the selection of the second-level detection points from the first-level detection points according to the detection waiting time includes: Sequentially select the i-th first-level detection point 1 from the first-level detection point sequence A as the target first-level detection point; Generate the relative waiting time coefficient t of the first-level detection point; i ; According to the matching evaluation value between the first-level detection point and the coal sample to be measured and the relative waiting time coefficient of the first-level detection point , obtain the comprehensive evaluation value W of the first-level detection point; i ; W i =Q 1 *P 1 * +Q 2 *P 2 *βi ; Among them, Q 1 is the preset first fixed coefficient, and Q 2 is the preset second fixed coefficient, and P 1 is the preset first weight coefficient, and P 2 is the preset second weight coefficient, is the i-th primary detection point and the matching evaluation value of the coal sample to be measured, and β i is the primary detection point 's relative waiting time coefficient; Calculate the comprehensive evaluation values of the coal sample to be measured and other primary detection points in sequence; Select the primary detection point sequence A 1 The primary detection point with the highest comprehensive evaluation value in is the secondary detection point.

[0035] Specifically, all parameters in the model are normalized by the preset first fixed coefficient and second fixed coefficient, so that each parameter is within the same value range.

[0036] Specifically, the higher the comprehensive evaluation value of the coal sample to be measured and the primary detection point, the higher the efficiency and accuracy of heat detection using the primary detection point.

[0037] Specifically, the generation of the primary detection point 's relative waiting time coefficient includes: According to the primary detection point sequence A 1 Select in sequence as the target primary detection point; Calculate the detection waiting time t required for the coal sample to be measured to be sent to the target primary detection point for detection i , t i = max( , ), where is the time consumed on the way from the position of the coal sample to be measured to the position of the target primary detection point, is the time required for the target primary detection point to complete the current task; Calculate the detection waiting time required for the coal sample to be measured to be sent to other primary detection points for detection; Generate the detection waiting time sequence T required for the coal sample to be measured to be detected by the coal heat detection point, T = (t 1 , t 2 … t i … t n1 ), where t i is the detection waiting time required for the coal sample to be measured to be sent to the i-th primary detection point for detection; n 1 is the number of primary detection points; Generate the relative waiting time coefficient β of the i-th primary detection point according to the detection waiting time sequence T i ; ; Among them, β i has a value range of (0, 1), t min is the minimum value in the sequence T, and t max is the maximum value in the sequence T.

[0038] It can be understood that this application sets up multiple coal calorific value detection points, generates the matching evaluation values of the coal sample to be tested and each coal calorific value detection point, sets the primary detection points according to all the matching evaluation values, selects the secondary detection points from the primary detection points according to the detection waiting time, and performs calorific value detection on the coal sample to be tested through the secondary detection points. This can not only improve the detection accuracy, but also improve the detection efficiency and shorten the sample waiting time.

[0039] In the preferred embodiment of this application, the judgment of whether to generate a correction instruction according to the coal sample calorific value detection result and the coal sample calorific value prediction result includes: Perform a primary verification on the coal sample calorific value detection result according to the effectiveness of the coal sample calorific value detection process; Perform a secondary verification on the coal sample calorific value detection result according to the credibility of the coal sample calorific value detection result; If one of the two verifications fails, generate a correction instruction.

[0040] Specifically, the primary verification of the coal sample calorific value detection result according to the effectiveness of the coal sample calorific value detection process includes: Preset the first effectiveness threshold y 1 ; Calculate the effectiveness y of the coal sample calorific value detection process; y = *u i ; Among them, k is the number of evaluation indicators of the coal sample calorific value detection process, is the preset weight coefficient of the i-th evaluation indicator, and u i is the evaluation value of the i-th evaluation indicator; Perform a primary verification on the coal sample calorific value detection result; When y < y 1 , the primary verification fails and a correction instruction is generated; When y y 1 , the primary verification passes and a secondary verification is performed on the coal sample calorific value detection result.

[0041] Specifically, the greater the effectiveness of the coal sample calorific value detection process, the more compliant the current coal sample calorific value detection process is.

[0042] Specifically, the evaluation indexes in the process of coal heat detection include: whether the oxygen bomb has good airtightness, whether the calorimeter has been calibrated for temperature balance, whether the oxygen pressure and oxygen filling time meet the standards, and whether the coal sample is completely burned, etc.

[0043] Specifically, the secondary verification of the coal sample heat detection result according to the credibility of the coal sample heat detection result includes: Presetting the first credibility threshold g 1 ; Calculating the fitting degree z between the coal sample heat detection result and the coal sample heat prediction result; ; Among them is the coal sample heat prediction result, is the coal sample heat detection result; Calculating the credibility g of the coal sample heat detection result according to the effectiveness of the coal sample heat detection process and the fitting degree between the coal sample heat detection result and the coal sample heat prediction result; g = Q 3 *P 3 *y + Q 4 *P 4 *z; Among them, Q 3 is the preset third fixed coefficient, Q 4 is the preset fourth fixed coefficient, P 3 is the preset third weight coefficient, P 4 is the preset fourth weight coefficient, y is the effectiveness of the coal sample heat detection process, and z is the fitting degree between the coal sample heat detection result and the coal sample heat prediction result; When g < g 1 , the secondary verification fails and a correction instruction is generated; When g g 1 , the secondary verification passes and the coal sample heat detection result is uploaded to the remote central control terminal.

[0044] Specifically, the greater the fitting degree between the coal sample heat detection result and the coal sample heat prediction result, the closer the coal heat detection result is to the coal heat prediction result.

[0045] Specifically, the higher the credibility of the coal heat detection result, the more reliable the coal heat detection result is.

[0046] Specifically, all parameters in the model are normalized by presetting the third fixed coefficient and the fourth fixed coefficient, so that each parameter is within the same value range.

[0047] Specifically, the correction instruction includes: Redo the calorific value detection on the coal sample to be tested; Generate the comprehensive evaluation values of each primary detection point in the coal sample to be tested and the primary detection point sequence A 1 in the middle; Remove the comprehensive evaluation values corresponding to the primary detection points that were selected as secondary detection points last time, and sort the remaining comprehensive evaluation values in descending order; Select the primary detection points with the top L comprehensive evaluation values to test the coal sample to be tested, and obtain L groups of coal sample calorific value detection results; Generate the coal sample calorific value detection result sequence C, C=(c 1 ,c 2 …c i …c L ), where c i is the calorific value detection result of the i-th group of coal samples; L is the number of groups of coal sample calorific value detections; Preset the second effectiveness threshold y 2 , and screen the coal sample calorific value detection result sequence C, and select the coal sample calorific value detection results with an effectiveness greater than y 2 during the coal sample calorific value detection process; Establish the screened coal sample calorific value detection result sequence C 1 ,C 1 =( , … … ), is the calorific value detection result of the i-th group of screened coal samples, L1 is the number of groups of screened coal sample calorific value detections, and L1 L; Calculate the coal sample calorific value detection result c' according to the screened coal sample calorific value detection result sequence C 1 ; ; Upload the coal sample calorific value detection result c' to the remote central control terminal.

[0048] It can be understood that in the above embodiments, it is determined whether to generate a correction instruction according to the coal sample calorific value detection result and the coal sample calorific value prediction result, and the coal sample calorific value detection result is verified once according to the effectiveness of the coal sample calorific value detection process; the coal sample calorific value detection result is verified twice according to the credibility of the coal sample calorific value detection result; after both verifications are passed, the coal sample calorific value detection result is uploaded to the remote central control terminal, otherwise a correction instruction is generated and the coal sample calorific value detection result is obtained again. This further ensures the effectiveness of the detection and greatly enhances the reliability and accuracy of the detection result.

[0049] In the preferred embodiment of the present application, determining whether to generate a maintenance instruction according to all abnormal risk values includes: Preset the first abnormal risk value threshold X 1 and the second abnormal risk value threshold X 2 , and X 1 < X 2 ; Select a i from the coal calorific value detection point sequence A in turn as the target coal calorific value detection point; Generate the abnormal risk value x i of the i-th coal calorific value detection point a at the current evaluation time node; i ; x i = Q 5 * P 5 * + Q 6 * P 6 * + Q 7 * P 7 * ([[]] - ) * H(i) where Q 5 is the preset fifth fixed coefficient, Q 6 is the preset sixth fixed coefficient, Q 7 is the preset seventh fixed coefficient, P 5 is the preset fifth weight coefficient, P 6 is the preset sixth weight coefficient, P 7 is the preset seventh weight coefficient, is the total number of first verification failures of the i-th coal calorific value detection point since the last maintenance, is the total number of second verification failures of the i-th coal calorific value detection point since the last maintenance, is the time since the last maintenance of the i-th coal calorific value detection point, is the preset standard maintenance time, H(i) is the selection coefficient, when ( - ) > 0, H(i) = 1, otherwise H(i) = 0; When x i < X 1 , the i-th coal calorific value detection point a i does not generate a maintenance instruction; When X 1 < x i < X 2 , the i-th coal calorific value detection point a i generates a first-level maintenance instruction; When X 1 < x i , for the i-th coal calorific value detection point a iGenerate secondary maintenance instructions; Generate the abnormal risk values of each coal calorific value detection point at the current evaluation time node in sequence, and determine whether to generate maintenance instructions according to the abnormal risk values.

[0050] It can be understood that in the above embodiments, by generating the abnormal risk values of each detection point and performing hierarchical maintenance according to the abnormal risk values, not only can the failure rate of the detection points be effectively reduced, the service life of the equipment be extended, but also the maintenance cost and downtime be reduced, and the stability of the system be improved.

[0051] Specifically, the greater the abnormal risk value of the coal calorific value detection point, the greater the possibility of risks occurring during the operation of the coal calorific value detection point.

[0052] Specifically, all parameters in the model are normalized by presetting a fifth fixed coefficient, a sixth fixed coefficient, and a seventh fixed coefficient, so that each parameter is within the same value range.

[0053] Specifically, the primary maintenance instruction is simple maintenance, which involves simply cleaning the instrument, checking whether accessories such as the connecting wires and sensors of the instrument are normal, and ensuring that the instrument is placed stably; the secondary maintenance instruction is in-depth maintenance, which involves deeply cleaning key components such as the calorimeter and the oxygen bomb, including disassembly and cleaning, checking whether components such as the threads, sealing rings, and insulating pads of the oxygen bomb are worn or damaged, replacing them if necessary, and recalibrating the calorimeter.

[0054] According to the first concept of the present application, multiple coal calorific value detection points are set up in the present application, the matching evaluation values of the coal sample to be measured and each coal calorific value detection point are generated, the primary detection points are set according to all the matching evaluation values, the secondary detection points are selected from the primary detection points according to the detection waiting time, and the calorific value of the coal sample to be measured is detected through the secondary detection points. This not only improves the detection accuracy, but also improves the detection efficiency and shortens the sample waiting time.

[0055] According to the second concept of the present application, the present application determines whether to generate a correction instruction according to the coal sample calorific value detection result and the coal sample calorific value prediction result, and performs a first verification on the coal sample calorific value detection result according to the effectiveness of the coal sample calorific value detection process; performs a second verification on the coal sample calorific value detection result according to the credibility of the coal sample calorific value detection result; after both verifications are passed, the coal sample calorific value detection result is uploaded to the remote central control terminal, otherwise a correction instruction is generated and the coal sample calorific value detection result is obtained again. This further ensures the effectiveness of the detection and greatly enhances the reliability and accuracy of the detection result.

[0056] According to the third concept of the present application, by generating the abnormal risk value of each detection point and performing hierarchical maintenance according to the abnormal risk value, the present application can not only effectively reduce the failure rate of the detection point, extend the service life of the equipment, but also reduce the maintenance cost and downtime, and improve the stability of the system.

[0057] The above are only the preferred embodiments of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the technical principle of the present invention, several improvements and substitutions can be made, and these improvements and substitutions should also be regarded as the protection scope of the present invention.

Claims

1. A remote intelligent detection method for coal heat index based on wireless calorimeter, characterized in that: Including: Establish multiple coal calorific value detection points according to the equipment parameters in the plant area; Obtain the parameters of the coal sample to be measured, and generate a predicted calorific value result of the coal sample according to the preset calorific value prediction model and the parameters of the coal sample to be measured; Generate a matching evaluation value between the coal sample to be measured and each coal calorific value detection point, set a first-level detection point according to all the matching evaluation values, and select a second-level detection point from the first-level detection points according to the detection waiting time; Obtain the coal sample calorific value detection result of the coal sample to be measured at the second-level detection point, and judge whether to generate a correction instruction according to the coal sample calorific value detection result and the coal sample calorific value prediction result; Generate an abnormal risk value for each coal calorific value detection point according to the preset evaluation time node, and judge whether to generate an overhaul instruction according to all the abnormal risk values; Among them, when setting up multiple coal calorific value detection points, it includes: Establish a coal heat detection point sequence A, A=(a1,a2…a i …a n ), where a i is the ith coal heat detection point; n is the number of coal heat detection points.

2. The remote intelligent detection method of coal heat index based on wireless calorimeter according to claim 1 is characterized in that: The generation of the matching evaluation value between the coal sample to be measured and each coal calorific value detection point includes: According to the coal heat detection point number column A, select a i It is the target coal heat detection point; Generate the coal sample to be tested and the i-th coal heat detection point a i The matching evaluation value λ i ; l i = ? Among them, m is the number of matching evaluation indicators, is the preset weight coefficient of the i-th matching evaluation index, is the reference value of the i-th matching evaluation index of the coal sample to be tested, is the reference value of the i-th coal heat detection point at the i-th matching evaluation index; Sequentially generate the matching evaluation value between the coal sample to be measured and other coal calorific value detection points.

3. The remote intelligent detection method of coal heat index based on wireless calorimeter according to claim 2 is characterized in that: The setting of the first-level detection point according to all the matching evaluation values includes: Preset the first matching evaluation value threshold λ'; According to the coal heat detection point number column A, select a i It is the target coal heat detection point; Judge whether to set the i-th coal calorific value detection point as the first-level detection point; When i >λ', the ith coal heat detection point is set as the first-level detection point; Sequentially judge whether to set other coal calorific value detection points as the first-level detection point; Establish a first-level detection point sequence, A1, A1=( , … … ), where a i is the i-th first-level detection point; n1 is the number of first-level detection points, n1 n.

4. The remote intelligent detection method of coal heat index based on wireless calorimeter according to claim 3 is characterized in that: The selection of the second-level detection point from the first-level detection points according to the detection waiting time includes: Select the i-th first-level detection point in sequence according to the first-level detection point sequence A1 It is the target first-level detection point; Generate first-level detection points The relative waiting time coefficient t i ; According to the first-level detection point Matching evaluation value and primary detection point with the coal sample to be tested The relative waiting time coefficient of the first-level detection point is obtained The comprehensive evaluation value W i ; W i =Q1*P1* +Q2*P2*β i ; Wherein, Q1 is a preset first fixed coefficient, Q2 is a preset second fixed coefficient, P1 is a preset first weight coefficient, and P2 is a preset second weight coefficient. is the i-th first-level detection point Matching evaluation value with the coal sample to be tested, β i First-level detection point The relative waiting time coefficient of Sequentially calculate the comprehensive evaluation value between the coal sample to be measured and other first-level detection points; Select the first-level detection point with the highest comprehensive evaluation value in the first-level detection point sequence A1 as the second-level detection point.

5. The remote intelligent detection method of coal heat index based on wireless calorimeter according to claim 4 is characterized in that: Generating a primary detection point The relative waiting time coefficients include: Select the first-level detection point column A1 in sequence It is the first-level detection point of the target; Calculate the waiting time t required for the coal sample to be sent to the target first-level detection point for detection i ,t i =max( , ),in, is the time consumed on the journey from the coal sample location to the target first-level detection point location, The time required to complete the current task for the target first-level detection point; Calculate the detection waiting time required for the coal sample to be measured to be detected by other first-level detection points; Generate the test waiting time series T required for the coal sample to be tested to pass through the coal heat detection point, T=(t1, t2…t i …t n1 ), where t i The waiting time required for the coal sample to be tested to be sent to the i-th primary testing point for testing; n1 is the number of primary testing points; Generate the relative waiting time coefficient β of the i-th primary detection point according to the detection waiting time series T i ; ; Among them, β i The value range is (0,1), t min is the minimum value in the sequence T, t max is the maximum value in the sequence T.

6. The remote intelligent detection method of coal heat index based on wireless calorimeter according to claim 5 is characterized in that: The judgment of whether to generate a correction instruction according to the coal sample calorific value detection result and the coal sample calorific value prediction result includes: Perform a primary verification on the coal sample calorific value detection result according to the effectiveness of the coal sample calorific value detection process; Perform a secondary verification on the coal sample calorific value detection result according to the credibility of the coal sample calorific value detection result; If one of the two verifications fails, generate a correction instruction.

7. The remote intelligent detection method of coal heat index based on wireless calorimeter according to claim 6 is characterized in that: The primary verification of the coal sample calorific value detection result according to the effectiveness of the coal sample calorific value detection process includes: Preset the first effectiveness threshold y1; Calculate the effectiveness y of the coal sample calorific value detection process; y= *u i ; Among them, k is the number of evaluation indicators in the coal sample heat detection process, is the preset weight coefficient of the i-th evaluation index, u i is the evaluation value of the i-th evaluation indicator; Perform a primary verification on the coal sample calorific value detection result; When y < y1, the primary verification fails, and generate a correction instruction; When At y1, if the first verification is passed, the heat detection results of the coal sample will be verified for the second time.

8. The remote intelligent detection method of coal heat index based on wireless calorimeter according to claim 7 is characterized in that: The secondary verification of the coal sample calorific value detection result according to the credibility of the coal sample calorific value detection result includes: Preset the first credibility threshold g1; Calculate the fitting degree z between the coal sample calorific value detection result and the coal sample calorific value prediction result; ; in The heat prediction result of the coal sample is The heat test result of coal sample; Calculate the credibility g of the coal sample calorific value detection result according to the effectiveness of the coal sample calorific value detection process and the fitting degree between the coal sample calorific value detection result and the coal sample calorific value prediction result; g = Q3 * P3 * y + Q4 * P4 * z; Wherein, Q3 is a preset third fixed coefficient, Q4 is a preset fourth fixed coefficient, P3 is a preset third weight coefficient, P4 is a preset fourth weight coefficient, y is the effectiveness of the coal sample calorific value detection process, and z is the fitting degree between the coal sample calorific value detection result and the coal sample calorific value prediction result; When g < g1, the secondary verification fails, and generate a correction instruction; When At g1, the secondary verification is passed and the coal sample heat detection results are uploaded to the remote central control terminal.

9. The remote intelligent detection method of coal heat index based on wireless calorimeter according to claim 8, characterized in that: The correction instruction includes: Redo the calorific value detection for the coal sample to be measured; Generate a comprehensive evaluation value of the coal sample to be tested and each first-level detection point in the first-level detection point array A1; Remove the comprehensive evaluation values ​​corresponding to the first-level detection points that were selected as second-level detection points last time, and arrange the remaining comprehensive evaluation values ​​in descending order; Select the first-level detection points with the top L comprehensive evaluation values ​​to detect the coal samples to be tested, and obtain the heat detection results of L groups of coal samples; Generate the coal sample heat detection result series C, C=(c1,c2…c i …c L ), where c i is the heat detection result of the i-th group of coal samples; L is the number of coal sample heat detection groups; A second validity threshold y2 is preset, and the coal sample heat detection result sequence C is screened to select the coal sample heat detection results whose validity of the coal sample heat detection process is greater than y2; Establish the series of heat detection results of the screened coal sample C1, C1=( , … … ), is the heat detection result of the coal sample after screening in the i-th group, L1 is the number of heat detection groups of the coal sample after screening, L1 L; Calculate the coal sample heat detection result c' according to the coal sample heat detection result series C1 after screening; ； The coal sample heat detection result c' is uploaded to the remote central control terminal.

10. The remote intelligent detection method of coal heat index based on wireless calorimeter according to claim 9, characterized in that: Determine whether to generate maintenance instructions based on all abnormal risk values, including: Preset the first abnormal risk value threshold X 1 and the second abnormal risk value threshold X 2 , and X 1 <X 2 ; According to the coal heat detection point number column A, select a i It is the target coal heat detection point; Generate the i-th coal heat detection point a i The abnormal risk value x at the current evaluation time node i ; x i =Q5*P5* +Q6*P6* +Q7*P7*( - )*H(i) Among them, Q5 is the preset fifth fixed coefficient, Q6 is the preset sixth fixed coefficient, Q7 is the preset seventh fixed coefficient, P5 is the preset fifth weight coefficient, P6 is the preset sixth weight coefficient, P7 is the preset seventh weight coefficient, is the total number of failed verifications at the ith coal heat detection point since the last overhaul, is the total number of secondary verification failures of the i-th coal heat detection point since the last maintenance, is the time from the last maintenance of the ith coal heat detection point, is the preset standard maintenance time, H(i) is the selection coefficient, when ( - )>0,H(i)=1, otherwise H(i)=0; When x i <X 1 When the i-th coal heat detection point a i No maintenance instructions are generated; When X 1 x i <X 2 When the i-th coal heat detection point a i Generate first-level maintenance instructions; When X 1 x i When the i-th coal heat detection point a i Generate secondary maintenance instructions; Generate the abnormal risk value of each coal heat detection point at the current evaluation time node in turn, and determine whether to generate a maintenance instruction based on the abnormal risk value.

Images