Intelligent operation and maintenance communication box

Abstract

The application discloses an intelligent operation and maintenance communication box, which realizes real-time intelligent monitoring on the operation state of the communication box by adding an optical power detection module and a power supply detection module; a mathematical model is established based on this, point position faults are predicted by linear regression, the demand of checking is determined, and whether the operation index is normal is judged; and a backend operation and maintenance platform is developed in combination with mathematical modeling, the operation and maintenance platform relies on big data calculation, realizes intelligent operation, intelligent repair and inspection and intelligent maintenance, and solves the problems that the traditional communication box relies on manual disposal, the equipment state is unknown, the fault checking efficiency is low, hidden dangers are not prewarned, and information access is difficult.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of communication boxes, and in particular to an intelligent operation and maintenance communication box. BACKGROUND

[0002] At present, the traditional communication boxes commonly used in China have many hidden troubles such as faults, maintenance difficulties, and social instability due to unreliable networks because they lack monitoring systems and intelligent management. In recent years, domestic communication box technology has made some progress in helping the high-quality development of communication networks, such as the environmental adaptability of the box body and the shell protection level. However, most of the box bodies are still in a single function structure state and cannot realize information system prevention, control and management. There are also some communication boxes with intelligent monitoring modules. For example, the E-generation home intelligent multimedia box has power distribution monitoring function, but it needs manual on-site viewing of the display screen, which is not convenient for monitoring. The Dongxu intelligent multimedia box has power distribution monitoring function, but needs to carry an additional server to realize background monitoring, which is high in cost. The Zhongkede intelligent communication box has power distribution monitoring, network monitoring and operation and maintenance platform, and has relatively perfect intelligent operation and maintenance function, but the selling price is as high as 6000 yuan, which is difficult for enterprises to bear. China's communication box technology still needs to make greater breakthroughs in high quality, intelligence and low cost. SUMMARY

[0003] The embodiments of the present application provide an intelligent operation and maintenance communication box to at least solve the technical problem of low fault handling efficiency of traditional communication boxes relying on manual handling in the related art.

[0004] According to an aspect of the embodiments of the present application, an intelligent operation and maintenance communication box is provided, comprising:

[0005] A power detection module is configured to monitor the current and voltage of power supply and distribution of end devices of the communication box.

[0006] An optical power detection module is configured to monitor the communication state of the communication box.

[0007] An operation and maintenance management platform is configured to analyze the current and voltage data, combine historical data in the database, extract RSR features through a rank-sum ratio comprehensive evaluation model, take the RSR data features as independent variables, predict point faults through a linear regression prediction model, determine the troubleshooting requirements, judge whether the operation indicators are normal, and output the prediction results as management decision basis.

[0008] Optionally, the current monitoring of the power detection module on the power supply and distribution of the end devices of the communication box comprises:

[0009] Detecting the voltage across the current sensing resistor of the power supply and distribution module of the communication box.

[0010] differential amplification is performed on the voltage across the current sensing resistor;

[0011] A / D conversion is performed on the differential amplified voltage, and the obtained current is divided by the previous differential amplification factor to restore the current data, thereby obtaining the current data.

[0012] Optionally, the power supply detection module performs voltage monitoring on the power supply and distribution of the end device of the communication box, including:

[0013] After the voltage is obtained by step-down isolation on the current of the power supply and distribution module of the communication box;

[0014] Differential amplification is performed on the voltage;

[0015] A / D conversion is performed on the differential amplified voltage, and the obtained voltage value is divided by the previous differential amplification factor to restore the voltage data, thereby obtaining the voltage data.

[0016] Optionally, the optical power detection module uses a photoresistor for detection.

[0017] Optionally, for data analysis of the current and voltage, combining historical data in the database, extracting RSR features through a rank-sum ratio comprehensive evaluation model, taking RSR data features as independent variables, predicting point faults through a linear regression prediction model, determining the need for investigation, determining whether the operation index is normal, and outputting the prediction result as a management decision basis, including the following steps:

[0018] Extracting feature data from the historical data of the communication box;

[0019] Determine whether the feature data has an abnormal value, if there is an abnormal value, remove the abnormal value and enter the next step, otherwise directly enter the next step;

[0020] Extract RSR features of each feature data from the feature data through a rank-sum ratio comprehensive evaluation model, and calculate the weight of each feature data;

[0021] According to the RSR sorting, a certain number of key features are extracted;

[0022] According to the key features, a linear prediction model is established, the input of the linear prediction model is the feature data of each index, and the output of the linear prediction model is the prediction point fault result.

[0023] Optionally, it also includes determining the need for investigation according to the prediction point fault result, and determining whether the operation index is normal.

[0024] Optionally, the linear prediction model is fitted by the least square method.

[0025] Optionally, the expression of the linear prediction model is:

[0026] Y = -0.68 + 0.23X1 + 0.868X2 + 1.036X3 + 0.022X4 + 0.05X5 + 0.71X6 + 0.8X7 + 0.06X8

[0027] In the above formula, Y is the dependent variable, indicating various types of fault indicators to be predicted, X i is the independent variable, indicating the input key features.

[0028] Compared with the prior art, the present application has the following beneficial effects:

[0029] In the embodiment of the present application, the running state of the communication box is intelligently monitored in real time by adding a light power detection module and a power supply detection module. A mathematical model is established on this basis to predict point faults by linear regression, determine the investigation requirements, and judge whether the operation indicators are normal. The back-end operation and maintenance platform is developed in combination with mathematical modeling. The operation and maintenance platform relies on big data calculation to realize intelligent operation, intelligent repair and inspection, and intelligent maintenance. The problems of relying on manual disposal, unknown device state, low fault investigation efficiency, no hidden danger warning, and difficult information access of traditional communication boxes are solved. In network operation, the intelligent communication box can perform real-time device state monitoring, power supply monitoring, and network state monitoring. When the maintenance personnel perform maintenance, the intelligent operation and maintenance platform can intelligently analyze and process faults, support remote fault repair, quickly locate fault positions, and accurately investigate hidden dangers through big data analysis. BRIEF DESCRIPTION OF DRAWINGS

[0030] In order to more clearly illustrate the technical solutions of the present application, the following will briefly introduce the drawings needed to be used in the embodiment description. Obviously, the drawings in the following description are only one embodiment of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0031] Figure 1 is a structural schematic diagram of an intelligent operation and maintenance communication box according to an embodiment of the present application;

[0032] Figure 2 is a structural schematic diagram of an intelligent operation and maintenance communication box according to an embodiment of the present application;

[0033] Figure 3 is a light power detection circuit diagram according to an embodiment of the present application;

[0034] Figure 4 is a current sampling circuit diagram according to an embodiment of the present application;

[0035] Figure 5 is a voltage sampling circuit diagram according to an embodiment of the present application;

[0036] Figure 6 is a work flow chart of a power detection module according to an embodiment of the present application;

[0037] Figure 7 is a flow chart of a prediction point fault analysis according to an embodiment of the present application;

[0038] Figure 8 is a fitting effect diagram according to an embodiment of the present application. DETAILED DESCRIPTION

[0039] It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other without conflict. The technical solutions in the embodiments of the present application will be described in detail below with reference to the drawings and in combination with the embodiments.

[0040] In order to enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should belong to the scope of protection of the present application.

[0041] It should be noted that the terms "first", "second" and the like in the specification and claims of the present application and the above-described drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or a chronological sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, device, product or equipment including a series of steps or units does not necessarily limit to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or equipment.

[0042] Embodiment 1

[0043] As Figure 1 is a structural diagram of an intelligent operation and maintenance communication box according to an embodiment of the present application, as Figure 1 shown, the intelligent operation and maintenance communication box includes a communication box, and further includes:

[0044] a power detection module, configured to monitor the current and voltage of power supply and distribution of the end device of the communication box, the communication box being connected with the end device;

[0045] a light power detection module, configured to monitor the communication state of the communication box;

[0046] The operation and maintenance management platform analyzes and processes the current and voltage data through mathematical modeling, combines it with historical data in the database, extracts RSR features through the rank-sum ratio comprehensive evaluation model, uses the RSR data features as independent variables, predicts point faults through a linear prediction model, determines troubleshooting needs, judges whether the operating indicators are normal, and outputs the prediction results as the basis for management decisions.

[0047] The aforementioned intelligent operation and maintenance communication box replaces manual monitoring with an optical power detection module, which avoids the problems of traditional optical power testing relying on manual operation at both ends of the optical fiber, which is cumbersome and has a high error rate.

[0048] As an optional embodiment, such as Figure 2 This is a schematic diagram of the internal structure of the intelligent operation and maintenance communication box according to an embodiment of the present invention, as shown below. Figure 2 As shown, for aesthetic purposes, the communication box panel uses bottom and rear wiring, with network cables and power cords connected at the bottom. For ease of wiring and maintenance, a rotating plug-in structure is used, allowing the module's back to be flipped to the front around a pivot.

[0049] As an optional embodiment, the optical power detection module is installed inside the communication box to monitor the communication status of the box by collecting light. Optical power monitoring commonly uses semiconductor photodetectors, which are greatly affected by temperature and introduce significant noise, leading to unstable test results. To automate the test and make it more stable, this embodiment utilizes the linear relationship between the light resistance of a photoresistor and illumination. The optical power detection module uses a GL5539 photoresistor for measurement, and data processing is performed by a TMS320 microcontroller. The specific circuit is as follows... Figure 3 As shown, the photocurrent of the test photoresistor GL5539 is automatically collected through the IDC port of the TMS320 microcontroller, converted into a digital signal by A / D conversion, and the optical power value is calculated according to formula (1).

[0050] I=K×U×a×L×b(1)

[0051] In the formula, I is the current through the photoresistor; U is the voltage applied to the photoresistor; L is the illuminance on the photoresistor; a is the voltage index; b is the illuminance index; and K is the proportionality coefficient. All of the above parameters are provided by the manufacturer.

[0052] The optical power detection module transmits the detected data to the operation and maintenance management platform for big data analysis and calculation, used to monitor abnormal conditions at the monitoring points. Detection using a photoresistor ensures stable test results, is less affected by environmental factors, and eliminates the need for manual light adjustment.

[0053] As an optional embodiment, such as Figure 6 As shown, the power detection module monitors the current and voltage at the power input terminal of the communication box through a current sampling circuit and a voltage sampling circuit.

[0054] Specifically, as shown in Figure 4 , the process of current sampling circuit monitoring includes: collecting the voltage across the current sensing resistor of the power supply module of the communication box; differentially amplifying the voltage across the current sensing resistor through a differential operational amplifier; inputting the differentially amplified voltage to the TMS320FADC sampling IO port, and dividing the obtained current by the previous differential amplification factor to obtain the measured current data.

[0055] Figure 5 As shown, the voltage monitoring of the power supply access end of the communication box by the power supply detection module includes: obtaining an isolated voltage after the current of the power supply module of the communication box is stepped down and isolated; differentially amplifying the isolated voltage; dividing the obtained voltage by the previous differential amplification factor to restore the voltage data and obtain the measured voltage data.

[0056] The power supply detection module transmits the detected data to the operation and maintenance management platform for big data analysis and calculation, for monitoring point position abnormality.

[0057] The power supply detection module described above uses differential operational amplifier circuit technology, effectively suppresses the zero drift phenomenon of the input signal, and controls the noise. Compared with ordinary integrated operational amplifier circuit, the accuracy of the output signal is improved. At the same time, the signal amplification function is realized, and the recognition degree of the signal is improved. The collected current and voltage signals are more accurate. At the same time, the circuit uses AC sampling to improve the collection speed and effectively reduce the delay. A / D conversion uses 12-bit chips to improve the precision. Secondly, a hardware wave filter circuit is set to improve the anti-interference ability.

[0058] As an optional embodiment, specifically, as shown in Figure 7 , the operation and maintenance management platform combines historical data in the database, extracts data RSR features through a rank sum ratio comprehensive evaluation model, takes the RSR data features as independent variables, predicts point position faults through a linear regression model, determines the troubleshooting requirements, judges whether the operation indicators are normal, and outputs the prediction results as management decision basis. Including the following steps:

[0059] Step S1, extracting feature data from historical data of the communication box, wherein the historical data includes: power supply detection module monitoring data, optical power detection module monitoring data and point position historical fault data, etc., and the historical data is stored in the database.

[0060] Step S2, judging whether the feature data has an abnormal value, when there is an abnormal value, the abnormal value is excluded and enters step S3, otherwise directly enters step S3;

[0061] The method for judging whether the characteristic data has an abnormal value is that the historical data obeys a normal distribution, and the probability of data falling outside the average value 3delta is P(|x-mu|>3delta) <=0.003, wherein x is an actual measurement sample, mu is a sample average value, and delta is a sample variance, which belongs to an extremely small probability event. Therefore, it is defined as an abnormal value, that is, an abnormal value is a value deviating from an average value by more than 3 times a standard deviation in input test values.

[0062] Step S3, a dimensionless statistic RSR of each characteristic data is extracted from the characteristic data by a rank sum ratio comprehensive evaluation model, a weight of each characteristic data is obtained, and RSR sorting is performed on the advantages and disadvantages of the characteristic data;

[0063] Specifically, the rank sum ratio comprehensive evaluation model adopts a spass statistical tool to calculate the weight of each type of index corresponding to the characteristic data obtained in step S2 by using an entropy weight method: the greater the variation degree of the index value, the smaller the information entropy, and the more information it can provide. Conversely, the same is true.

[0064] Step S4, a certain number of key characteristics are extracted according to the RSR sorting.

[0065] Specifically, the top 8 key characteristics in the sorting are selected as input data for subsequent fault determination.

[0066] Step S5, a linear prediction model is established according to the key characteristics, the input of the linear prediction model is the characteristic data of each index, and the output of the linear prediction model is a predicted point fault result.

[0067] The linear prediction model is fitted by using a least square method.

[0068] Specifically, the expression of the linear prediction model is:

[0069] Y1=-0.68+0.23X1+0.868X2+1.036X3+0.022X4+0.05X5+0.71X6+0.8X7+0.06X8(2)

[0070] In the above formula, Y is a dependent variable, indicating various fault indexes to be predicted, X i is an independent variable, indicating 8 key characteristics input.

[0071] The data characteristics such as current and voltage are taken as input X, the linear regression prediction equation in formula (2) is used to calculate the fault index, the result shows that the predicted value and the true value are perfectly fitted, and the fitting effect is as Figure 8 The dependent variable Y1 can be set as a predicted point fault, a confirmation of troubleshooting requirements, a determination of an operating state, and other parameters to be predicted, which are all predicted by the same model and no longer repeated.

[0072] Step S6, when the device is working normally, manually measure the current voltage and other data characteristics X in normal state, and calculate the operation index Y2 of the device when working normally according to formula (2), and record in the database. When it is necessary to predict whether the device is working normally, test the current voltage and other data characteristics X of the power supply and distribution and optical power module, and calculate Y1 by using formula (2). When the absolute error of Y1 and Y2 is less than 2, it is judged that the predicted operation index is in normal state.

[0073] The above-mentioned prediction point fault analysis adopts the rank sum ratio comprehensive evaluation model and the linear regression prediction model. The rank sum ratio comprehensive evaluation method only calculates the respective weight according to the characteristics of the data itself, and extracts the key data. Compared with the expert model, the influence of subjective factors is excluded, the evaluation result is more objective and accurate, and the advantage is most obvious when the data amount is large enough. When predicting point faults, judging the demand for troubleshooting and confirming the operation index of the device, the least square method is used for linear regression prediction. The least square method finds the best match of the equation coefficients by minimizing the sum of squares of errors. The dependent variable can be easily obtained, and the sum of squares of errors between the dependent variable and the true data is minimized. Because the point does not fail every day, and there is no troubleshooting demand every day. The time span of the event is large, and usually one failure occurs every three or four months, and the time interval is irregular. Therefore, using time series prediction will bring a large error. The linear regression prediction result by the least square method is more accurate.

[0074] As an optional embodiment, the database software of the operation and maintenance management platform adopts MySQL, and the development language adopts java language.

[0075] The units described as separate components can or can not be physically separated, and the components displayed as units can or can not be physical units, that is, they can be located in one place, or they can be distributed to multiple units. Part or all of the units can be selected to achieve the purpose of the embodiment of the present application according to actual needs.

[0076] In addition, the functional units in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware, or in the form of software functional unit.

[0077] The integrated unit, if implemented in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application, essentially or in other words, the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, including a number of instructions to make a computer device (which can be a personal computer, a server or a network device, etc.) execute all or part of the steps of the methods described in various embodiments of the present application. The aforementioned storage medium includes: a U disk, a read-only memory (ROM, Read-0nly Memory), a random access memory (RAM, Random Access Memory), a mobile hard disk, a magnetic disk or an optical disk, and various media that can store program codes.

[0078] The above is only the preferred embodiment of the present application, it should be pointed out that, for those skilled in the art, without departing from the principles of the present application, can make a number of improvements and refinements, these improvements and refinements should also be considered as the protection scope of the present application.

Claims

1. An intelligent operation and maintenance communication box, comprising a communication box, characterized in that, Also include: Power detection module, for the power supply of the communication box of the end device current and voltage monitoring; Optical power detection module, for monitoring the communication state of the communication box; Operation and maintenance management platform, for data analysis of the current and voltage, combined with the historical data in the database, through the rank sum ratio comprehensive evaluation model to extract the RSR characteristics, taking the RSR characteristics as the independent variable, through the linear regression prediction model to predict the point fault, determine the investigation demand, judge whether the operation index is normal, the output prediction result as the basis for management decision; The data analysis of the current and voltage, combined with the historical data in the database, through the rank sum ratio comprehensive evaluation model to extract the RSR characteristics, taking the RSR characteristics as the independent variable, through the linear regression prediction model to predict the point fault, determine the investigation demand, judge whether the operation index is normal, the output prediction result as the basis for management decision, including the following steps: From the historical data of the communication box, the feature data is extracted; Determine whether the characteristic data has abnormal value, when there is abnormal value, the abnormal value is excluded and the next step is entered, otherwise directly enter the next step; Through the rank sum ratio comprehensive evaluation model, the RSR of each characteristic data is extracted from the characteristic data, and the weight of each characteristic data is obtained; According to the RSR sorting, a certain number of key characteristics are extracted as the RSR characteristics; According to the key characteristics, a linear prediction model is established, the input of the linear prediction model is the characteristic data of each index, and the output of the linear prediction model is the prediction point fault result; The number is 8; The linear prediction model is fitted by least square method; The expression of the linear prediction model is: Y=-0.68+0.23X1+0.868X2+1.036X3+0.022X4+0.05X5+0.71X6+0.8X7+0.06X8; In the above formula, Y is the dependent variable, representing various types of failure indicators that need to be predicted, X i is the independent variable, representing the input key features, i∈{1,2,3,4,5,6,7,8}.

2. The intelligent operation and maintenance communication box according to claim 1, characterized in that, The current monitoring of the power supply of the communication box of the end device of the power supply detection module includes: Detecting the voltage across the current sensing resistor of the power supply module of the communication box; Differential amplification is carried out on the voltage across the current sensing resistor; According to the voltage after differential amplification, A / D conversion is carried out, the obtained current is divided by the previous differential amplification multiple, and the current data is restored, so as to obtain the current data.

3. The intelligent operation and maintenance communication box according to claim 1, characterized in that, The voltage monitoring of the power supply of the communication box of the end device of the power supply detection module includes: Obtain the isolation voltage after the current of the power supply module of the communication box is isolated by voltage reduction; Differential amplification is carried out on the isolation voltage; According to the voltage after differential amplification, A / D conversion is carried out, the obtained voltage value is divided by the previous differential amplification multiple, and the voltage data is restored, so as to obtain the voltage data.

4. The intelligent operation and maintenance communication box according to claim 1, characterized in that, The optical power detection module adopts photosensitive resistor for detection.

5. The intelligent operation and maintenance communication box according to claim 1, characterized in that, Also include: According to the prediction point fault result, determine the investigation demand, judge whether the operation index is normal.

Images