Information service system based on big data

Abstract

The invention relates to the technical field of information service, in particular to an information service system based on big data. Comprising an information processing module and an information service module. An equipment health assessment table is generated by monitoring the temperature, the output power, the vibration amplitude and the current spectrogram of key parts of the instrument in real time, so that headquarter personnel are helped to know the state of the instrument at any time, the change trend of the state of the equipment can be identified, and reliable data support is provided for timely fault early warning and maintenance suggestions; slopes of adjacent evaluation points are calculated through a data fitting technology, an abnormal state value is accurately calculated in combination with a central value, and the system can accurately identify the abnormal degree of the instrument. According to intelligent comparison between an abnormal state value and a set interval, the system provides accurate guidance suggestions, so that the maintenance strategy of the instrument is optimized, and timely and effective intervention measures are ensured; by dynamically adjusting the collection frequency, the monitoring efficiency is remarkably improved, and the resource utilization rate is maximized.

Description

Technical Field

[0001] The present invention relates to the field of information service technology, and in particular to an information service system based on big data. Background Art

[0002] For health service companies with multiple chain stores, the complexity of management is mainly reflected in the large number of stores, complicated departments, and significantly increased difficulty in coordination and communication; in addition, each store is equipped with a variety of instruments, especially those high-end equipment that are expensive. These instruments generate massive amounts of data during the reception of customers and autonomous operation; the traditional manual recording and management methods are not only prone to errors and omissions, but also difficult to meet the needs of modern and refined management; therefore, it is very necessary to realize information services for multiple stores;

[0003] The current information service systems are mostly focused on data recording, storage and query, lacking in-depth data mining and intelligent analysis capabilities. They are unable to display the status of each instrument through data analysis, making it difficult for headquarters managers to intuitively view the status of the instruments. Summary of the invention

[0004] The purpose of the present invention is to provide an information service system based on big data to solve the problems mentioned in the above background technology.

[0005] The object of the present invention can be achieved by the following technical solutions: An information service system based on big data includes: a server, an information processing module and an information service module;

[0006] The information processing module performs monitoring and analysis based on the instrument information to obtain the evaluation value, constructs a two-dimensional rectangular coordinate system with the monitoring time as the horizontal coordinate and the evaluation value as the vertical coordinate, inputs the evaluation value corresponding to each monitoring moment in the monitoring window into the coordinate axis, and records the position of the evaluation value in the coordinate axis as the evaluation point, uses line segments to connect each evaluation point in sequence to obtain a health evaluation diagram of the monitoring window, and sends it to the information service module;

[0007] The information service module performs graphic analysis based on the received health assessment graph to obtain the abnormal state value of the monitoring window, and generates guidance suggestions accordingly; the specific graphic analysis process is as follows:

[0008] Retrieve the line graph of the changes in the evaluation value of the monitoring window, use data fitting to calculate the slope of the line segment composed of two adjacent evaluation points and record it as the evaluation slope, and calculate the mean of the evaluation values ​​corresponding to the two adjacent points to obtain the central value of the adjacent evaluation points;

[0009] Set the instrument to a usage factor φ and compare it with the evaluation slope and the center value The abnormal state value corresponding to the monitoring window is obtained by formula calculation and analysis. The specific calculation formula is:

[0010]

[0011] Where δ1 and δ2 are respectively set proportional constants; j = 1, 2, 3...J, J is a positive integer, J represents the total number of monitoring moments in the monitoring window, and j represents the number of any monitoring moment in the monitoring window; when When k is an even number, the abnormal state value increases with Increase and increase; when When <0, k is a cardinality, and the abnormal state value increases with Increase and decrease;

[0012] Select a monitoring window closest to the current time, and compare and analyze the corresponding abnormal state value with the set abnormal interval. When the abnormal state value is greater than the maximum value in the set abnormal interval, make a "maintenance offline" guidance suggestion;

[0013] When the abnormal status value is within the set abnormal range, the guidance advice of "follow-up monitoring" is given and the collection frequency is adjusted; when the abnormal status value is less than the minimum value in the set abnormal range, the guidance advice of "maintaining monitoring" is given.

[0014] Preferably, it also includes a server;

[0015] Through the received acquisition frequency, information acquisition instructions are sent to each store to update the instrument information. The specific instrument information includes the temperature, output power, vibration amplitude and current spectrum of each key part.

[0016] Preferably, the specific acquisition frequency adjustment method is: obtain the current acquisition frequency and record it as R' and the abnormal state value corresponding to the acquisition frequency and record it as UY', and set the proportional formula The most recent acquisition frequency is calculated and sent to the server to control the information acquisition of the instrument.

[0017] Preferably, the calculation and analysis process of the usage coefficient is:

[0018] Retrieve the historical usage records and historical fault records of the instrument. The specific usage records include the number of uses and the start and end times of each use; the historical fault records include the number of faults and the start and end times of each fault; match the nearest monitoring window in time based on the start and end times of each use, and mark the abnormal state value of the monitoring window as the winning value, thereby obtaining the winning value of each use;

[0019] The time difference between the start time and the end time of each use is calculated to obtain the usage duration of each use, and the time difference is normalized with the corresponding winning bid value and the numerical value is taken, and the numerical value is weighted to obtain the usage value of each use; the usage value of each use is summed up to obtain the usage mean;

[0020] The time difference between the start time and the end time of each fault is calculated to obtain the fault duration of each fault, and the average value is calculated to obtain the average fault duration; the number of faults is counted, and the average fault duration is normalized and the value is taken, and the value is weighted to obtain the fault value;

[0021] The mean value A1 and the fault value A2 are used to set the formula φ = ln (θ1 × e A1 +θ2×e A2 +1) is calculated and analyzed to obtain the usage coefficient φ, where θ1 and θ2 are the set proportional constants respectively.

[0022] Preferably, the specific process of monitoring and analyzing the instrument information to obtain the evaluation value is as follows:

[0023] 5-1: Retrieve the instrument information at each monitoring moment. The specific instrument information includes the temperature of each key part (the key part here refers to the important parts of the instrument, such as the motor, laser head, infrared emission source, etc. of the instrument), the output power recorded as Pj, the vibration amplitude recorded as Fj and the current spectrum I(t); t represents the time domain of the current spectrum, that is, the time dimension;

[0024] 5-2: Analyze the temperature sensitivity of the instrument according to the temperature of each key part of the instrument to obtain the temperature performance value, thereby obtaining the temperature performance value at each monitoring time;

[0025] 5-3: The current spectrum I(t) in the time domain is converted into the frequency domain spectrum I(f) by fast Fourier transform. The characteristic elements of the spectrum are obtained by feature extraction based on the frequency domain spectrum. The specific characteristic elements of the spectrum include: the amplitude ratio R of each harmonic n , total harmonic distortion ratio H and high frequency noise value G h ; Assume that there is a current spectrum of the instrument in a normal state, and obtain a standard product and a spectrum through the above-mentioned time domain-frequency domain transformation. Similarly, extract the spectrum features of the standard product and the spectrum to obtain the spectrum characteristic elements; perform formula calculation and analysis on the spectrum characteristic elements of the frequency domain spectrum and the standard spectrum collected at each monitoring moment to obtain the current distortion value IQ, thereby obtaining the current distortion value at each monitoring moment and recording it as IQj; the specific calculation formula is:

[0026]

[0027] Among them, γ1, γ2, and γ3 are respectively set proportional coefficients, and their values ​​are set by those skilled in the art;

[0028] 5-4: Set each instrument to correspond to a standard output power, normalize the temperature performance value Lbj, output power Pj, standard output power BP, vibration amplitude Fj and current distortion value IQj at each monitoring time and take their values, and perform formula calculation and analysis on the values ​​to obtain the evaluation value PGj at each monitoring time. The specific calculation formula is:

[0029]

[0030] Among them, λ1, λ2, λ3, and λ4 are the set proportional constants respectively.

[0031] Preferably, the specific process of analyzing the temperature sensitivity of the instrument according to the temperature of each key part of the instrument is:

[0032] Set a temperature sensitivity value corresponding to each key part of each device, multiply the temperature of each key part by the corresponding temperature sensitivity value to obtain a weighted temperature value recorded as Qi j, where i = 1, 2, 3 ... I, I is a positive integer, I represents the total number of key parts in the instrument, and i represents the number of any key part in the instrument; compare and analyze the weighted temperature value with the set weighted interval, when the weighted temperature value is greater than the upper limit of the set weighted interval, a highly sensitive part is accumulated; when the weighted temperature value is within the set weighted interval, a medium sensitive part is accumulated; when the weighted temperature value is less than the lower limit of the set weighted interval, a slightly sensitive part is accumulated; count the cumulative number of highly sensitive parts, medium sensitive parts and slightly sensitive parts in the instrument respectively, and record them as L1, L2, and L3 respectively;

[0033] The cumulative number of highly sensitive parts L1, the cumulative number of medium sensitive parts L2, the cumulative number of slightly sensitive parts L3 and the weighted temperature value Qij of each key part are normalized and their values ​​are taken. The values ​​are calculated and analyzed by formula to obtain the temperature performance value Lb. The specific calculation formula is:

[0034]

[0035] b1, b2, and b3 are respectively set proportional coefficients, and b1>b2>b3>0.

[0036] Preferably, feature extraction is performed based on the frequency domain spectrogram, wherein the extraction process of the amplitude ratio of each harmonic is:

[0037] Identify the amplitude of the sine wave component corresponding to the power frequency in the frequency domain spectrum, record it as the fundamental amplitude, record it as I1, and identify the amplitude of other integer multiple frequencies, record it as I n, n is a positive integer greater than or equal to 2; by setting the formula Calculate the amplitude ratio R of each harmonic n .

[0038] Preferably, feature extraction is performed based on the frequency domain spectrogram, wherein the extraction process of the total harmonic distortion ratio is:

[0039] The fundamental amplitude I1 and each harmonic amplitude I n Through the distortion model The total harmonic distortion ratio H is calculated.

[0040] Preferably, feature extraction is performed based on the frequency domain spectrogram, wherein the extraction process of the high-frequency noise value is:

[0041] Identify the high frequency band in the frequency domain spectrum. The specific high frequency band is the part greater than the set frequency, and record the high frequency band in the spectrum as f h , the number of sampling points in the high frequency band is recorded as N h , which means the frequency range is in the high frequency band f h The number of discrete spectrum points in the internal spectrum; by setting the formula Calculate the amplitude mean μ h and standard deviation σ h , and perform weighted calculation to obtain the high-frequency noise value.

[0042] Beneficial effects of the present invention:

[0043] 1. Through real-time monitoring of the temperature, output power, vibration amplitude and current spectrum of key parts of the instrument, temperature sensitivity analysis and current distortion analysis are performed to obtain the evaluation value at each monitoring moment, and generate an equipment health evaluation table based on this, so as to help headquarters personnel understand the status of the instrument at any time, especially the expensive instruments; it can also identify the changing trend of the equipment status, and provide reliable data support for timely fault warning and maintenance suggestions;

[0044] 2. The system can accurately identify the degree of abnormality of the instrument by calculating the slope of adjacent evaluation points through data fitting technology and accurately calculating the abnormal status value in combination with the central value. Based on the intelligent comparison between the abnormal status value and the set interval, the system provides accurate guidance and suggestions for "repair offline", "follow-up monitoring" or "maintenance monitoring", thereby optimizing the maintenance strategy of the instrument and ensuring timely and effective intervention measures.

[0045] 3. By dynamically adjusting the acquisition frequency, not only the monitoring efficiency is significantly improved, but also the resource utilization is maximized. Through personalized information management and maintenance suggestions, the system can maximize the efficiency of instrument monitoring management, ensure that the instrument is always in the best operating state, and effectively reduce the risk of potential failures. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The present invention will be further described below in conjunction with the accompanying drawings.

[0047] Figure 1 It is a schematic diagram of system module connection of the present invention. DETAILED DESCRIPTION

[0048] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0049] See also Figure 1 As shown, the present invention is an information service system based on big data, comprising: a server, an information processing module and an information service module;

[0050] The server sends information acquisition instructions to each store through the received acquisition frequency to update the instrument information. The specific instrument information includes the temperature, output power, vibration amplitude and current spectrum of each key part. It should be noted that, for example, if the acquisition frequency is 2h, then the instrument information is collected every 2h. The monitoring window for each monitoring is set by the personnel in this field. The temperature, output power, vibration amplitude and current spectrum of each key part at each acquisition time are collected within the monitoring window. The current spectrum needs to continuously collect multiple data points in a very short time (usually 10 seconds or 15 seconds, etc.) to capture the current fluctuation characteristics. The specific performance is: the monitoring window is 30min, and the temperature, output power, vibration amplitude and current spectrum of each key part are collected every 2min within the monitoring window.

[0051] The information processing module monitors the instrument status in real time based on the instrument information to draw the equipment health assessment diagram and display it so that the headquarters staff can check it at any time and keep abreast of the dynamics of the instrument, especially the expensive instruments; further quantitative analysis is carried out based on the equipment health assessment table to give scientific suggestions and guidance, so that managers can understand the health status of the instrument more easily and simply, and provide more reference suggestions for them; specifically:

[0052] Retrieve the instrument information at each monitoring moment. The specific instrument information includes the temperature of each key part (the key part here refers to the important parts of the instrument, such as the motor, laser head, infrared emission source, etc. of the instrument), the output power is recorded as Pj, the vibration amplitude is recorded as Fj, and the current spectrum I(t), where j = 1, 2, 3...J, J is a positive integer, J represents the total number of monitoring moments in the monitoring window, j represents the number of any monitoring moment in the monitoring window; t represents the time domain of the current spectrum, that is, the time dimension; in the current spectrum I(t), the time domain signal describes the instantaneous change of the current over time;

[0053] Set a temperature sensitivity value for each key part of the equipment. Since different key parts have different electronic components and materials, their tolerance to temperature is different. Therefore, different key parts have different corresponding temperature sensitivity values. The larger the temperature sensitivity value, the less tolerant it is to temperature, which means that it is more likely to be affected or damaged when the temperature rises. Multiply the temperature of each key part by the corresponding temperature sensitivity value to get the weighted temperature value, which is recorded as Qi. j, where i = 1, 2, 3 ... I, I is a positive integer, I represents the total number of key parts in the instrument, and i represents the number of any key part in the instrument; compare and analyze the weighted temperature value with the set weighted interval. When the weighted temperature value is greater than the upper limit of the set weighted interval, a highly sensitive part is accumulated; when the weighted temperature value is within the set weighted interval, a medium sensitive part is accumulated; when the weighted temperature value is less than the lower limit of the set weighted interval, a slightly sensitive part is accumulated; the cumulative number of highly sensitive parts, medium sensitive parts and slightly sensitive parts in the instrument is counted respectively, and they are recorded as L1, L2, and L3 respectively; the cumulative number of highly sensitive parts L1, the cumulative number of medium sensitive parts L2, the cumulative number of slightly sensitive parts L3 and the weighted temperature value Qi j of each key part are normalized and their values ​​are taken, and the values ​​are calculated and analyzed by formula to obtain the temperature performance value Lb. The specific calculation formula is:

[0054]

[0055] Where b1, b2, and b3 are the set proportional coefficients respectively, and b1>b2>b3>0, so the temperature performance value corresponding to each monitoring time is recorded as Lbj;

[0056] The current spectrum I(t) in the time domain is converted into the frequency domain spectrum I(f) by fast Fourier transform (FFT), and the frequency domain spectrum is amplitude normalized so that the analysis results are not affected by the difference in sampling dimensions; the characteristic elements of the spectrum are obtained by feature extraction based on the frequency domain spectrum. The specific characteristic elements of the spectrum include: the amplitude ratio of each harmonic, the total harmonic distortion ratio and the high-frequency noise value. The specific feature extraction process is as follows:

[0057] Identify the amplitude of the sine wave component corresponding to the power frequency (such as 50Hz or 60Hz) in the frequency domain spectrum, record it as the fundamental amplitude and record it as I1, identify the amplitude of other integer multiple frequencies (such as the second harmonic 2f or the third harmonic 3f) and record it as I n (i.e., all harmonics except the fundamental wave), n is a positive integer greater than or equal to 2; through the set formula Calculate the amplitude ratio R of each harmonic n ;

[0058] The fundamental amplitude I1 and each harmonic amplitude I n Through the distortion model The total harmonic distortion ratio H is calculated; it should be noted that the present invention only considers the first 10 harmonics in the actual model building process, that is, in the actual process, only the value of n is calculated to be 10, but in a completely ideal case, the value of n is infinite;

[0059] Identify the high frequency band in the frequency domain spectrogram. The specific high frequency band is the part greater than the set frequency (for example, 10kHz), and record the high frequency band in the spectrum as f h , the number of sampling points in the high frequency band is recorded as N h , which means the frequency range is in the high frequency band f h The number of discrete spectrum points in the internal spectrum; by setting the formula Calculate the amplitude mean μ h and standard deviation σ h , and the high-frequency noise value is obtained by weighted calculation and recorded as G h It should be noted that when the amplitude mean μ h The larger the value, the greater the risk of abnormal operation of the equipment or the increase of external interference, and the greater the high-frequency noise value; when the standard deviation σ h The larger the value, the more unstable the high-frequency noise is. If the interference source is unstable or the equipment is not running smoothly, the higher the high-frequency noise value will be.

[0060] The amplitude of each harmonic is R n , total harmonic distortion ratio H and high frequency noise value G h As a spectral feature element of the frequency domain spectrogram;

[0061] Assume that there is a current spectrum of the instrument in normal state, and obtain the standard frequency domain spectrum through the above time domain-frequency domain transformation. Similarly, extract the spectrum features of the standard frequency domain spectrum to obtain the spectrum feature elements. The spectrum feature elements include the amplitude ratio of each harmonic, which is recorded as BR n , total harmonic distortion ratio is recorded as BH and high frequency noise value is recorded as BG h ;

[0062] The frequency domain spectrum acquired at each monitoring moment is analyzed and calculated by formulating the spectrum characteristic elements of the standard spectrum to obtain the current distortion value IQ. The current distortion value at each monitoring moment is recorded as IQj. The specific calculation formula is:

[0063]

[0064] Among them, γ1, γ2, and γ3 are respectively set proportional coefficients, and their values ​​are set by the personnel in this field. It can be seen from the formula that when the spectrum characteristic elements of the frequency domain spectrum are larger than the spectrum characteristic elements of the standard spectrum, it means that the current distortion of the instrument is more serious, and the current distortion value is larger;

[0065] Each instrument is set to correspond to a standard output power, denoted as BP. When the actual output power of the instrument is monitored to be less than the standard output power, it is a manifestation of instrument performance degradation, failure or reduced operating efficiency; conversely, when the actual output power of the instrument is monitored to be greater than the standard power, it means that the instrument has potential overload, potential failure or environmental interference, which has a negative impact on the instrument.

[0066] The temperature performance value Lbj, output power Pj, standard output power BP, vibration amplitude Fj and current distortion value IQj at each monitoring moment are normalized and their values ​​are taken. The values ​​are calculated and analyzed by formula to obtain the evaluation value PGj at each monitoring time. The specific calculation formula is:

[0067]

[0068] Among them, λ1, λ2, λ3, and λ4 are respectively set proportional constants. It can be seen from the formula that when the temperature performance value is larger, the instrument is more affected by temperature, and the evaluation value is larger; when the output power is closer to the standard output power, the evaluation value is smaller; when the vibration amplitude is larger, it means that the internal components are loose or the wear is more serious, and the evaluation value is larger; the larger the current distortion value, the larger the evaluation value; a two-dimensional rectangular coordinate system is constructed with time as the horizontal coordinate and the evaluation value as the vertical coordinate, and the evaluation value corresponding to each monitoring moment in the monitoring window is input into the coordinate axis, and the position of the evaluation value in the coordinate axis is recorded as the evaluation point, and each evaluation point is connected in sequence by a line segment to obtain a line graph of the evaluation value change in the monitoring window, and it is displayed; thus, a line graph of the evaluation value change of each instrument in any monitoring window can be obtained, and it is sent to the information service module;

[0069] By real-time monitoring of the temperature of key parts of the instrument, output power, vibration amplitude and current spectrum, temperature sensitivity analysis, current distortion analysis, etc. are performed to obtain the evaluation value at each monitoring moment, and an equipment health assessment form is generated based on this to help headquarters personnel understand the status of the instrument at any time, especially expensive instruments; it can also identify the changing trend of the equipment status and provide reliable data support for timely fault warnings and maintenance recommendations.

[0070] The information service module performs service management on the instrument based on the received monitoring window change line chart to achieve refined service management of each instrument, specifically:

[0071] Step 1: Retrieve the line graph of the changes in the evaluation value of the monitoring window, and use data fitting to calculate the slope of the line segment composed of two adjacent evaluation points as the evaluation slope It should be noted that when the evaluation slope is greater than zero, it means that the evaluation value increases; when the evaluation slope is less than zero, it means that the evaluation value decreases; the evaluation values ​​corresponding to two adjacent points are averaged to obtain the central value of the adjacent evaluation points, which is recorded as The slope will be evaluated and the center value Perform formulaic calculation and analysis to obtain the abnormal state value corresponding to the monitoring window. The specific calculation formula is:

[0072]

[0074] Among them, δ1 and δ2 are the set proportional constants, and φ is the usage coefficient; when When k is an even number, the abnormal state value increases with Increase and increase; when When k is a cardinality, the abnormal state value increases with Increase and decrease; thus, the abnormal state value corresponding to each monitoring window can be obtained;

[0075] Select a monitoring window closest to the current time, and compare and analyze the corresponding abnormal state value with the set abnormal interval. When the abnormal state value is greater than the maximum value in the set abnormal interval, it means that the instrument is seriously abnormal, and a "maintenance offline" guidance suggestion is made;

[0076] When the abnormal state value is within the set abnormal range, the guidance of "follow-up monitoring" is given and the acquisition frequency is adjusted. The specific adjustment method is: obtain the current acquisition frequency and record it as R' and the abnormal state value corresponding to the acquisition frequency and record it as UY', and use the set proportional formula Calculate and obtain the most recent acquisition frequency, and send it to the server to control the information acquisition of the instrument;

[0077] When the abnormal state value is less than the minimum value in the set abnormal range, a guidance suggestion of "maintain monitoring" is made;

[0078] Step 2: retrieve the historical usage records and historical fault records of the instrument. The specific usage records include the number of uses and the start and end times of each use; the historical fault records include the number of faults and the start and end times of each fault; match the nearest monitoring window in time according to the start and end times of each use, and mark the abnormal state value of the monitoring window as the winning value, thereby obtaining the winning value of each use;

[0079] The time difference between the start time and the end time of each use is calculated to obtain the use time of each use, and the time difference is normalized with the corresponding winning bid value and the value is taken, and the value is weighted to obtain the use value of each use; the use value of each use is summed up to obtain the use average value recorded as A1;

[0080] Step 3: Calculate the time difference between the start time and the end time of each fault to obtain the fault duration of each fault, and calculate the average fault duration; count the number of faults, normalize it with the average fault duration and take its value, perform weighted calculation on the value to obtain the fault value recorded as A2; It should be noted that the longer the use time, the greater the risk of overuse of the instrument; the longer the fault duration, the more serious the fault;

[0081] The mean value A1 and the fault value A2 are used to set the formula φ = ln (θ1 × e A1 +θ2×e A2 +1) to calculate and analyze to obtain the usage coefficient φ, where θ1 and θ2 are respectively the set proportional constants; the usage coefficient is updated to step 1;

[0082] By calculating the slopes of adjacent assessment points through data fitting technology and accurately calculating the abnormal status value in combination with the central value, the system can accurately identify the degree of abnormality of the instrument; based on the intelligent comparison of the abnormal status value with the set interval, the system provides accurate "repair offline", "follow-up monitoring" or "maintenance monitoring" guidance suggestions, thereby optimizing the instrument's maintenance strategy and ensuring timely and effective intervention measures; at the same time, the system dynamically adjusts the acquisition frequency, which not only significantly improves monitoring efficiency, but also maximizes resource utilization. Through personalized information management and maintenance suggestions, the system can maximize the efficiency of instrument monitoring management, ensure that the instrument is always in the best operating state, and effectively reduce the risk of potential failures.

[0083] The above contents are merely examples and explanations of the structure of the present invention. The technicians in this technical field may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the structure of the invention or exceed the scope defined by the claims, they should all fall within the protection scope of the present invention.

Claims

1. Information service system based on big data, including: Information processing module and information service module; characterized in that: The information processing module performs monitoring and analysis based on the instrument information to obtain the evaluation value, constructs a two-dimensional rectangular coordinate system with the monitoring time as the horizontal coordinate and the evaluation value as the vertical coordinate, inputs the evaluation value corresponding to each monitoring moment in the monitoring window into the coordinate axis, and records the position of the evaluation value in the coordinate axis as the evaluation point, uses line segments to connect each evaluation point in sequence to obtain a health evaluation diagram of the monitoring window, and sends it to the information service module; The information service module performs graphic analysis based on the received health assessment graph to obtain the abnormal state value of the monitoring window, and generates guidance suggestions accordingly; the specific graphic analysis process is as follows: Retrieve the line graph of the changes in the evaluation value of the monitoring window, use data fitting to calculate the slope of the line segment composed of two adjacent evaluation points and record it as the evaluation slope, and calculate the mean of the evaluation values ​​corresponding to the two adjacent points to obtain the central value of the adjacent evaluation points; Set a usage coefficient corresponding to the instrument, and perform a formulaic calculation and analysis on it, the evaluation slope and the center value to obtain the abnormal state value corresponding to the monitoring window; select a monitoring window closest to the current time, and compare and analyze its corresponding abnormal state value with the set abnormal interval. When the abnormal state value is greater than the maximum value in the set abnormal interval, make guidance suggestions for maintenance offline; When the abnormal status value is within the set abnormal range, guidance suggestions for follow-up monitoring are given and the collection frequency is adjusted; when the abnormal status value is less than the minimum value in the set abnormal range, guidance suggestions for maintaining monitoring are given.

2. The information service system based on big data according to claim 1 is characterized in that: Also includes servers; The server sends information acquisition instructions to each store through the received collection frequency to update the instrument information. The specific instrument information includes the temperature, output power, vibration amplitude and current spectrum of each key part.

3. The information service system based on big data according to claim 2 is characterized in that: The specific method of adjusting the acquisition frequency is: obtain the current acquisition frequency and the abnormal state value corresponding to the acquisition frequency, formulate the current acquisition frequency, the abnormal state value corresponding to the acquisition frequency and the abnormal state value of the monitoring window closest to the current time of the system to obtain the nearest acquisition frequency, and send it to the server to control the information collection of the instrument.

4. The information service system based on big data according to claim 1 is characterized in that: The calculation and analysis process of the utilization coefficient is as follows: Retrieve the historical usage records and historical fault records of the instrument. The specific usage records include the number of uses and the start and end times of each use; the historical fault records include the number of faults and the start and end times of each fault; match the nearest monitoring window in time based on the start and end times of each use, and mark the abnormal state value of the monitoring window as the winning value, thereby obtaining the winning value of each use; The time difference between the start time and the end time of each use is calculated to obtain the use time of each use, and the time difference is normalized with the corresponding winning bid value and the numerical value is taken, and the numerical value is weighted to obtain the use value of each use; The usage value of each use is summed up to obtain the usage mean; The time difference between the fault start time and the fault end time of each fault is calculated to obtain the fault duration of each fault, and the average of the time difference is calculated to obtain the average fault duration; The number of faults is counted, and normalized with the average fault length to obtain the value, and the value is weighted to obtain the fault value; The mean value and the failure value will be used to calculate and analyze the utilization factor.

5. The information service system based on big data according to claim 1 is characterized in that: The specific process of monitoring and analyzing the instrument information to obtain the evaluation value is as follows: 5-1: Retrieve the instrument information at each monitoring moment. The specific instrument information includes the temperature, output power, vibration amplitude and current spectrum I(t) of each key part; t represents the time domain of the current spectrum, i.e., the time dimension; 5-2: Analyze the temperature sensitivity of the instrument according to the temperature of each key part of the instrument to obtain the temperature performance value, thereby obtaining the temperature performance value at each monitoring time; 5-3: The current spectrum I(t) in the time domain is converted into the frequency domain spectrum I(f) by fast Fourier transform, and the characteristic elements of the spectrum are obtained by extracting the features according to the frequency domain spectrum. The specific characteristic elements of the spectrum include: the amplitude ratio of each harmonic, the total harmonic distortion ratio and the high-frequency noise value; it is assumed that there is a current spectrum in the normal state of the instrument, and it is subjected to the above-mentioned time domain-frequency domain transformation to obtain a standard frequency domain spectrum. Similarly, the spectrum feature extraction of the standard frequency domain spectrum is performed to obtain the spectrum characteristic elements; the frequency domain spectrum collected at each monitoring time and the spectrum characteristic elements of the standard spectrum are calculated and analyzed by formulating and analyzing to obtain the current distortion value; 5-4: Set each instrument to correspond to a standard output power, normalize the temperature performance value, output power, standard output power, vibration amplitude and current distortion value at each monitoring moment and take their numerical values, perform formula calculation and analysis on the numerical values ​​to obtain the evaluation value of each monitoring time.

6. The information service system based on big data according to claim 5 is characterized in that: The specific process of analyzing the temperature sensitivity of the instrument based on the temperature of each key part of the instrument is as follows: Set a temperature sensitivity value corresponding to each key part of each device, multiply the temperature of each key part by the corresponding temperature sensitivity value to obtain a weighted temperature value; compare and analyze the weighted temperature value with the set weighted interval. When the weighted temperature value is greater than the upper limit of the set weighted interval, a highly sensitive part is accumulated; when the weighted temperature value is within the set weighted interval, a medium sensitive part is accumulated; when the weighted temperature value is less than the lower limit of the set weighted interval, a slightly sensitive part is accumulated; Count the cumulative number of highly sensitive parts, medium sensitive parts and slightly sensitive parts of the instrument respectively; The cumulative number of highly sensitive parts, the cumulative number of medium sensitive parts, the cumulative number of slightly sensitive parts and the weighted temperature values ​​of each key part are normalized and their numerical values ​​are taken, and the numerical values ​​are calculated and analyzed by formula to obtain the temperature performance value.

7. The information service system based on big data according to claim 5 is characterized in that: Feature extraction is performed based on the frequency domain spectrum, and the extraction process of the amplitude ratio of each harmonic is as follows: Identify the amplitude of the sine wave component corresponding to the power frequency in the frequency domain spectrum, record it as the fundamental amplitude, record it as I1, and identify the amplitude of other integer multiple frequencies, record it as I n , n is a positive integer greater than or equal to 2; by setting the formula Calculate the amplitude ratio R of each harmonic n .

8. The information service system based on big data according to claim 7 is characterized in that: Feature extraction is performed based on the frequency domain spectrum, where the extraction process of the total harmonic distortion ratio is: The fundamental amplitude I1 and each harmonic amplitude I n Through the distortion model The total harmonic distortion ratio H is obtained by calculation.

9. The information service system based on big data according to claim 8, characterized in that: Feature extraction is performed based on the frequency domain spectrogram, where the extraction process of high-frequency noise value is: Identify the high frequency band in the frequency domain spectrum. The specific high frequency band is the part greater than the set frequency, and record the high frequency band in the spectrum as f h , the number of sampling points in the high frequency band is recorded as N h , which means the frequency range is in the high frequency band f h The number of discrete spectrum points in the internal spectrum; by setting the formula Calculate the mean amplitude μ h and standard deviation σ h , and perform weighted calculation to obtain the high-frequency noise value.

Images