A fault prediction system for laboratory ventilation equipment based on data analysis

Abstract

The present invention discloses a fault prediction system for laboratory ventilation equipment based on data analysis, including an emission operation acquisition module, an environmental parameter acquisition module, an emission environment corrosion analysis module, an emission analysis module, a data fusion analysis module, an emission analysis module and a data service platform. The present invention can analyze the corrosion estimated accelerated damage coefficient of each type of gas emitted to the ventilation equipment and use a data prediction fusion formula to estimate the predicted time corresponding to the ventilation equipment reaching a preset exhaust duct leakage caliber threshold from the current state, and analyze the error offset corresponding to the predicted time in combination with the data service platform to dynamically compensate for the predicted time, thereby improving the accuracy of the predicted time of continuous emission of gas by the ventilation equipment and improving the safety of the laboratory environment.

Description

Technical Field

[0001] The invention belongs to the technical field of laboratory ventilation equipment and relates to a fault prediction system for laboratory ventilation equipment based on data analysis. Background Art

[0002] In the daily analysis and experiment process in the laboratory, various unpleasant, corrosive, toxic, harmful or flammable and explosive gases and other pollution sources are often generated. If the harmful gases and solid particles are not discharged outdoors in time, it will cause indoor air pollution, affect the health and safety of the experimenters, and affect the accuracy and service life of the analytical instruments and equipment. Common ventilation equipment in laboratories includes fume hoods, which are commonly used exhaust equipment in physical and chemical laboratories. Their purpose is to control, dilute and exhaust toxic and harmful substances such as smoke, aerosol, particles, and acidic, alkaline and corrosive gases generated by the experiment, etc., to protect laboratory researchers from the harm of toxic and harmful chemicals generated by the experiment.

[0003] As the ventilation equipment in the existing laboratories discharges acidic, alkaline and corrosive gases, the inner wall of the ventilation duct will be corroded, which will then lead to the gradual increase of the corrosion diameter of the ventilation duct, affecting the ventilation equipment's effective discharge of the gases generated in the laboratory, and thus resulting in the inability to promptly eliminate the harmful substances generated during the experiment, endangering the health of the experimenters and the safety of the equipment in the laboratory. At the same time, when predicting the failure of the ventilation equipment, it is impossible to eliminate the interference between the various failures that cause the ventilation equipment. Summary of the invention

[0004] The purpose of the present invention is to provide a fault prediction system for laboratory ventilation equipment based on data analysis, which solves the problems existing in the existing background technology.

[0005] The purpose of the present invention can be achieved through the following technical solutions:

[0006] A fault prediction system for laboratory ventilation equipment based on data analysis, including an emission operation acquisition module, an environmental parameter acquisition module, an emission environment corrosion analysis module, an emission volume analysis module, a data fusion analysis module, an emission volume analysis module and a data service platform;

[0007] The emission operation collection module collects the operating parameters of each ventilation device in the laboratory, and sends the collected operating parameters of each ventilation device to the emission analysis module;

[0008] The environmental parameter collection module includes several environmental parameter collection units, which collect the concentration of various gas types in the environment in the area in real time;

[0009] The emission environment corrosion analysis module extracts the gas concentration corresponding to each type of gas emitted cumulatively by each ventilation device, the emission time, and the humidity and temperature values ​​in the ventilation device corresponding to each type of gas emitted, analyzes the corrosion acceleration damage coefficient of each gas type on the ventilation device in the emission environment, and sends the analyzed corrosion acceleration damage coefficient of each gas type on the ventilation device to the data fusion analysis module;

[0010] The emission analysis module obtains the operating parameters of the ventilation equipment in each area collected by the emission operation collection module, extracts the working power of the ventilation equipment in the operating parameters, and selects the theoretical emission gas volume LQ corresponding to the ventilation equipment power per unit time T according to the working power of the ventilation equipment;

[0011] The data fusion analysis module extracts the estimated accelerated damage coefficient of corrosion of each gas type on the ventilation equipment, performs data prediction fusion processing on the estimated accelerated damage coefficient of corrosion of each gas type on the ventilation equipment and the duration of each gas type previously discharged by the laboratory, predicts the predicted duration corresponding to the ventilation equipment reaching the set exhaust duct leakage diameter threshold from the current state, and feeds back the analyzed predicted duration to the data service platform;

[0012] The data service platform extracts the predicted time corresponding to the ventilation equipment reaching the set exhaust duct leakage diameter threshold from the current state sent by the data fusion analysis module, and extracts the emission time and emission gas concentration of each gas type in the sampling time period in real time, and calculates the error offset of the predicted time combined with the average value SQ of the actual emission gas volume of the ventilation equipment in the sampling time period, and uses the error offset to dynamically adjust the predicted time.

[0013] Furthermore, the exhaust environment corrosion analysis module analyzes the estimated corrosion damage coefficient of each gas type on the ventilation equipment within a fixed monitoring time period, including the following steps:

[0014] Step A1, extracting the gas concentration when the ventilation equipment reaches the emission conditions for acidic, alkaline and corrosive gases, as well as the temperature, humidity and emission time during the emission process, and establishing a gas emission matrix L;

[0015] Step A2, extracting the gas concentration of each gas type recorded in the gas emission matrix and the time required for the gas to be completely discharged, and analyzing the gas emission concentration decay rate;

[0016] Step A3: using a corrosion damage prediction model to analyze the corrosion acceleration damage coefficient of each gas type discharged from the ventilation equipment on the ventilation equipment.

[0017] Furthermore, the formula of the corrosion damage prediction model is: Pi is the estimated accelerated damage coefficient of corrosion of the ventilation equipment under the interference of the i-th exhaust gas, ci is the unit gas concentration of the i-th gas type, unit is mg / m3, βi is the corrosion proportional coefficient corresponding to the unit gas concentration of the i-th gas type, unit is m3 / mg, wp is the set standard humidity, wb is the set standard temperature, xi1 is the gas concentration corresponding to the i-th gas type under the exhaust condition of the ventilation equipment, xi4 is the time required for the i-th gas type to be discharged through the ventilation equipment, and Vi is the exhaust concentration decay rate of the i-th gas type.

[0018] Furthermore, the emission analysis module also extracts the wind speed V in the operating parameters, uses the wind volume calculation formula to analyze the actual emission gas volume of the ventilation equipment per unit time, analyzes the theoretical emission gas volume and the actual emission gas volume SQ, and obtains the gas emission attenuation coefficient.

[0019] Furthermore, the data fusion analysis module adopts the data prediction fusion formula in the process of data prediction fusion processing: RS is the average theoretical amount of gas emitted by the ventilation equipment at different working frequencies, WS is the average actual amount of gas emitted by the ventilation equipment at different working frequencies at the current moment, XS is the average actual amount of gas emitted by the ventilation equipment at different working frequencies when the ventilation equipment reaches the set threshold of exhaust duct leakage diameter, so as to eliminate the large deviation of the predicted duration caused by different working frequencies of the ventilation equipment, and improve the prediction of the sustainable emission duration of the gas. E is the predicted sustainable emission duration of the gas, e is a natural number, and ui is the total emission duration of the i-th gas type in the laboratory in the past.

[0020] Furthermore, the error offset calculation formula of the prediction duration is: e is a natural number, yi is the gas concentration required to be emitted by the i-th gas type during the sampling period, bi is the emission duration of the i-th gas type during the sampling period, vi is the predicted sustainable emission duration of the gas, and the average emission rate of the i-th gas type emitted by the ventilation equipment in the past at time E. is the error offset coefficient of the prediction duration.

[0021] Furthermore, the fault prediction system of the laboratory ventilation equipment also includes a fault emission training module, which extracts the actual emission gas quantities of the ventilation equipment at different operating frequencies under different fault types and the theoretical emission gas quantities under different operating frequencies, performs decentralized training on the actual emission gas quantities under each fault type under the same operating frequency, obtains the standardization of the actual emission gas quantities after decentralized training, and analyzes the emission output interference measurement corresponding to each fault type.

[0022] Furthermore, the actual emission gas volume of different fault types under the same working frequency is dispersedly trained. The specific training method is as follows:

[0023] Step 1: extract the actual emission gas volume of different fault types under the same working frequency, and the number of times the actual emission gas volume of each fault type is extracted is the same, that is, the number of samples extracted for the same fault type under the same working frequency is f;

[0024] Step 2: Establish a sample training feature table;

[0025] Step 3: Standardize the actual exhaust gas volume corresponding to each fault type to obtain a standardized training sample BQ j , k is the total number of samples, k = C*N*f, C is the number of operating frequencies of the ventilation equipment, that is, frequency 1, frequency 2, frequency 3, C is 3, N is the number of fault types, SQ j is the actual emission gas volume corresponding to the jth sample in the sample training feature table;

[0026] Step 4: extract standard training samples corresponding to different fault types under the same operating frequency;

[0027] Step 5: The emission output interference measurement model is used to analyze the emission output interference measurement corresponding to each fault type, which can accurately eliminate the dynamic interference degree of the fault type on the exhaust condition of the ventilation equipment under the working frequency interference.

[0028] Furthermore, the formula of the emission output interference measurement model in step 5 is: a(BQ c ) is the exhaust output interference measure corresponding to the cth fault type, η c is the exhaust weight proportional coefficient corresponding to the cth fault type, z is equal to 1, 2, 3, c is 1, 2, ..., N, which is the actual exhaust gas volume corresponding to the cth fault type of the ventilation equipment at the zth operating frequency. is the actual exhaust gas volume corresponding to the cth fault type of the ventilation equipment at the zth operating frequency, and

[0029] Beneficial effects of the present invention:

[0030] The present invention analyzes the concentration of each gas type emitted cumulatively by the ventilation equipment, the emission time, and the temperature and humidity inside the ventilation equipment during the emission process to obtain the estimated accelerated damage coefficient of corrosion of the ventilation equipment caused by each gas type emitted, and can directly obtain the degree of corrosion damage of the ventilation equipment caused by each gas during the emission process.

[0031] The present invention adopts a data prediction fusion formula to comprehensively estimate and analyze the corrosion acceleration damage coefficient of the ventilation equipment during the emission of each type of gas, as well as the time and emission gas volume of each type of gas emitted by the ventilation equipment in the past, and estimates the predicted time corresponding to the preset exhaust duct leakage diameter threshold of the ventilation equipment from the current state, and analyzes the error offset corresponding to the predicted time in combination with the data service platform to dynamically compensate for the predicted time, thereby improving the accuracy of the predicted time of continuous gas emission of the ventilation equipment. Once the predicted time is approached, the ventilation duct can be repaired in time to reduce the inability to effectively emit harmful gases due to pipeline corrosion and damage, thereby improving the safety of the laboratory environment.

[0032] The present invention analyzes the emission output interference measurement corresponding to each fault type through a fault emission training module, reduces the impact of different fault types on the dispersion of actual emission gas volume under the same operating frequency, and can accurately analyze the emission output interference measurement corresponding to each fault type to avoid the dynamic interference of each fault type on the exhaust of the ventilation equipment due to different operating frequencies, thereby reducing the accuracy of the prediction of each fault type. DETAILED DESCRIPTION

[0033] The following will be combined with 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.

[0034] A fault prediction system for laboratory ventilation equipment based on data analysis includes an emission operation acquisition module, an environmental parameter acquisition module, an emission environment corrosion analysis module, an emission volume analysis module, a data fusion analysis module, an emission volume analysis module, a data service platform and a fault emission training module.

[0035] The emission operation collection module collects the operating parameters of each ventilation device in the laboratory, and sends the collected operating parameters of each ventilation device to the emission analysis module.

[0036] The operating parameters of the ventilation equipment include wind pressure, wind speed, ventilation equipment frequency, and temperature and humidity inside the ventilation equipment.

[0037] The environmental parameter acquisition module includes a plurality of environmental parameter acquisition units, and the environmental parameter acquisition units collect the concentration of various gas types in the environment in the area in real time.

[0038] Each environmental parameter collection unit is distributed in each area one by one. Ventilation equipment and environmental parameter collection units are provided in each area. A mutual mapping relationship between the same ventilation equipment and the environmental parameter collection unit is established. The selected ventilation equipment is a fume hood.

[0039] The types of gases collected include carbon dioxide, chlorine, ammonia, nitrogen oxides, hydrogen fluoride, sulfur dioxide, hydrogen sulfide, carbon monoxide, methane, acetylene, ethylene, propane, butane, propylene, propyne, 1,3-butadiene, butyne, hydrogen sulfide, etc.

[0040] The emission environment corrosion analysis module extracts the gas concentration corresponding to each gas type emitted cumulatively by each ventilation device, the emission time, and the humidity and temperature values ​​inside the ventilation device corresponding to each gas type emitted, analyzes the estimated accelerated damage coefficient of corrosion of the ventilation device by each gas type in the emission environment, and sends the analyzed estimated accelerated damage coefficient of corrosion of the ventilation device by each gas type to the data fusion analysis module.

[0041] According to the estimated damage coefficient of corrosion of ventilation equipment by various types of gases emitted cumulatively by ventilation equipment, it is judged that the acidic, alkaline and corrosive gases generated in the laboratory will cause corrosion and damage to the ventilation equipment when passing through the ventilation equipment and ventilation equipment pipes. The corrosion of the ventilation equipment will cause air leakage when the ventilation equipment is in use, and the harmful gases generated in the laboratory cannot be effectively discharged stably.

[0042] Specifically, the emission environment corrosion analysis module analyzes the estimated corrosion damage coefficient of each gas type on the ventilation equipment within a fixed monitoring time period, including the following steps:

[0043] Step A1: Extract the gas concentration when the ventilation equipment reaches the emission conditions for acidic, alkaline and corrosive gases, as well as the temperature, humidity and emission time during the emission process, and establish a gas emission matrix i=1,2,...,m, where m is the total number of times the gas type is discharged through the ventilation equipment and recorded in chronological order, xi1 is the gas concentration corresponding to the i-th gas type that meets the discharge conditions of the ventilation equipment, xi2 is the humidity inside the ventilation equipment during the discharge process of the i-th gas type discharged through the ventilation equipment, xi3 is the temperature inside the ventilation equipment during the discharge process of the i-th gas type discharged through the ventilation equipment, and xi4 is the time required for the i-th gas type to be discharged through the ventilation equipment.

[0044] Step A2: extract the gas concentration xi1 of each gas type recorded in the gas emission matrix and the time xi4 required for the gas to be completely discharged, and analyze the gas emission concentration decay rate

[0045] Step A3, using a corrosion damage prediction model to analyze the corrosion acceleration damage coefficient of each gas type discharged from the ventilation equipment on the ventilation equipment;

[0046] Among them, the formula of the corrosion damage prediction model is: Pi is the estimated accelerated damage coefficient of corrosion of the ventilation equipment under the interference of the i-th exhaust gas, ci is the unit gas concentration of the i-th gas type, unit is mg / m3, βi is the corrosion proportional coefficient corresponding to the unit gas concentration of the i-th gas type, unit is m3 / mg, wp is the set standard humidity, and wb is the set standard temperature.

[0047] By analyzing the environmental parameters in the ventilation equipment and the concentration of each gas emitted when each type of gas generated in the laboratory is discharged through the ventilation equipment, it is possible to predict the degree of corrosion and damage to the ventilation equipment caused by the emitted corrosive and acidic and alkaline gases, and to quantitatively display the specific numerical degree of damage to the ventilation duct caused by a single type of gas. In addition, with the corrosive effect of corrosive, acidic and alkaline gases in special environments, the pipes in the ventilation equipment and the ventilation equipment body (or the valve plate of the non-return air valve in the ventilation equipment) can be corroded and fallen off, resulting in air leakage in the ventilation equipment, which affects the emission efficiency of harmful gases generated in the laboratory.

[0048] The emission analysis module obtains the operating parameters of the ventilation equipment in each area collected by the emission operation collection module, extracts the working power of the ventilation equipment in the operating parameters, and screens out the theoretical emission gas volume LQ corresponding to the power of the ventilation equipment per unit time T according to the working power of the ventilation equipment. At the same time, the wind speed V in the operating parameters is extracted, and the actual emission gas volume of the ventilation equipment per unit time is analyzed using the wind volume calculation formula. The theoretical emission gas volume and the actual emission gas volume SQ are analyzed to obtain the gas emission attenuation coefficient By performing differential analysis on the theoretical emission gas amount and the actual emission gas amount, the emission attenuation coefficient of the actual emission gas amount relative to the theoretical emission gas amount can be determined.

[0049] The actual exhaust gas volume SQ is calculated as SQ=V*D*T, where D is the open area of ​​the fume hood operating window, V is the wind speed at the operating window, and T is the unit time.

[0050] The data fusion analysis module extracts the estimated accelerated damage coefficient of corrosion of each gas type on the ventilation equipment, and performs data prediction fusion processing on the estimated accelerated damage coefficient of corrosion of each gas type on the ventilation equipment and the duration of each gas type previously emitted by the laboratory, and predicts the predicted duration corresponding to the ventilation equipment reaching the set exhaust duct leakage diameter threshold from the current state (the set exhaust duct leakage diameter threshold is the cumulative area of ​​the duct leakage diameter corresponding to the preset emission lower limit value of the exhaust gas discharged by the ventilation equipment), and feeds back the analyzed predicted duration to the data service platform.

[0051] The data fusion analysis module uses the data prediction fusion formula in the process of data prediction fusion processing: RS is the average theoretical amount of gas emitted by the ventilation equipment at different working frequencies, WS is the average actual amount of gas emitted by the ventilation equipment at different working frequencies at the current moment, XS is the average actual amount of gas emitted by the ventilation equipment at different working frequencies when the ventilation equipment reaches the set threshold of exhaust duct leakage diameter, so as to eliminate the large deviation of the predicted duration caused by different working frequencies of the ventilation equipment, and improve the prediction of the sustainable emission duration of the gas. E is the predicted sustainable emission duration of the gas, e is a natural number, and ui is the total emission duration of the i-th gas type in the laboratory in the past.

[0052] The data fusion analysis module can predict the sustainable emission time of the gas when the ventilation equipment's pipe reaches the set exhaust pipe leakage diameter threshold from the current state. In the process of predicting the sustainable emission time of the ventilation equipment, it is necessary to ensure that the ventilation equipment has no other faults, otherwise it will affect the accuracy of the prediction.

[0053] The data service platform extracts the predicted time corresponding to the ventilation equipment reaching the set exhaust duct leakage diameter threshold from the current state sent by the data fusion analysis module, and extracts the emission time and emission gas concentration of each gas type in the sampling time period in real time. Combined with the average value SQ of the actual emission gas volume of the ventilation equipment in the sampling time period, the predicted time is calculated with error offset, and the predicted time is dynamically adjusted using the error offset. The adjusted predicted time is In order to ensure the accuracy of the predicted duration of ventilation equipment failure, it is convenient to make adjustments based on the actual gas emissions of the ventilation equipment during the sampling period. The data of air leakage in the ventilation equipment pipeline can be displayed intuitively, and manual maintenance or replacement of the pipeline can be reminded.

[0054] The calculation formula for the error offset of the prediction duration is: e is a natural number, yi is the gas concentration required to be emitted by the i-th gas type during the sampling period, bi is the emission duration of the i-th gas type during the sampling period, vi is the predicted sustainable emission duration of the gas, and the average emission rate of the i-th gas type emitted by the ventilation equipment in the past at time E. is the error offset coefficient of the prediction duration.

[0055] The error offset calculation formula is used to calculate the error offset of the predicted duration E to obtain the error offset coefficient, and the sustainable emission duration of the ventilation equipment is dynamically adjusted according to the error offset coefficient to continuously adjust the sustainable emission duration, thereby achieving further optimization of the predicted duration and ensuring that the error between the dynamically adjusted predicted duration and the actual sustainable emission duration is smaller, thereby improving the accuracy of the predicted duration. Once the predicted duration is approached, the ventilation duct can be repaired in time to reduce the inability to effectively discharge harmful gases due to pipeline corrosion and damage, thereby improving the safety of the laboratory environment.

[0056] The fault emission training module extracts the actual emission gas volume of ventilation equipment under different operating frequencies under different fault types and the theoretical emission gas volume under different operating frequencies, and performs decentralized training on the actual emission gas volume under each fault type under the same operating frequency, obtains the standardization of the actual emission gas volume after decentralized training, and analyzes the emission output interference measurement corresponding to each fault type. The sampling decentralized training can obtain the impact of different fault types on the dispersion of the actual emission gas volume under the same operating frequency, and uses standardized processing to eliminate the interference of the operating frequency, and then accurately analyzes the emission output interference measurement corresponding to each fault type, so as to avoid the dynamic interference of each fault type on the exhaust of the ventilation equipment caused by different operating frequencies, and reduce the accuracy of the prediction of each fault type.

[0057] The actual emission gas volume of different fault types under the same working frequency is dispersedly trained. The specific training method is as follows:

[0058] Step 1: extract the actual emission gas volume of different fault types under the same operating frequency. The number of times the actual emission gas volume of each fault type is extracted is the same, that is, the number of samples extracted for the same fault type under the same operating frequency is f.

[0059] The types of faults include air leakage in the exhaust duct, damage to the anti-reverse air valve, fan failure, motor failure, inverter abnormality, and unstable power supply voltage.

[0060] For the types of exhaust duct leakage faults, during the decentralized training process, state training is carried out with different leakage levels. Taking the set exhaust duct leakage diameter as the standard, the powder exhaust duct leakage is divided into the first leakage level, the second leakage level, and the third leakage level. The first leakage level means that the size of the exhaust duct leakage port is smaller than the set exhaust duct leakage diameter, the second leakage level means that the size of the exhaust duct leakage port is smaller than 2 times the set exhaust duct leakage diameter and larger than the set exhaust duct leakage port, and the third leakage level means that the size of the exhaust duct leakage port is larger than 2 times the set leakage diameter.

[0061] Step 2: Establish a sample training feature table, that is, the sample training feature table records multiple groups of sample training feature sub-tables, each group of sample training feature sub-tables records the actual exhaust gas volume corresponding to each fault type under the same working frequency and the theoretical exhaust gas volume of the ventilation equipment under the working frequency, and is sorted from large to small according to the working frequency;

[0062] Step 3: Standardize the actual exhaust gas volume corresponding to each fault type to obtain a standardized training sample BQ j , k is the total number of samples, k = C*N*f, C is the number of operating frequencies of the ventilation equipment, that is, frequency 1, frequency 2, frequency 3, C is 3, N is the number of fault types, SQ j is the actual emission gas volume corresponding to the jth sample in the sample training feature table;

[0063] Step 4: extract standard training samples corresponding to different fault types under the same operating frequency;

[0064] Step 5: The emission output interference measurement model is used to analyze the emission output interference measurement corresponding to each fault type, which can accurately eliminate the dynamic interference degree of the fault type on the exhaust condition of the ventilation equipment under the working frequency interference.

[0065] Among them, the formula of the emission output interference measurement model is: a(BQ c ) is the exhaust output interference measure corresponding to the cth fault type, η c is the exhaust weight proportional coefficient corresponding to the cth fault type, z is equal to 1, 2, 3, c is 1, 2, ..., N, which is the actual exhaust gas volume corresponding to the cth fault type of the ventilation equipment at the zth operating frequency. is the actual exhaust gas volume corresponding to the cth fault type of the ventilation equipment at the zth operating frequency, and

[0066] By analyzing the emission output interference measurement corresponding to each fault type, sampling dispersion training can obtain the impact of different fault types on the dispersion of actual emission gas volume under the same working frequency, and use standardized processing to eliminate the interference of the working frequency, and then accurately analyze the emission output interference measurement corresponding to each fault type, so as to avoid the dynamic interference of each fault type on the exhaust of the ventilation equipment caused by different working frequencies, reduce the accuracy of the prediction of each fault type, and at the same time, classify each fault type differently.

[0067] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technical personnel in this field according to actual conditions. The size of the proportional coefficient and the weight coefficient is to quantify each parameter to obtain a specific value, which is convenient for subsequent comparison. Regarding the size of the proportional coefficient and the weight coefficient, as long as it does not affect the proportional relationship between the parameter and the quantized value, it is fine.

[0068] The above contents are merely examples and explanations of the concept 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 concept 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. A fault prediction system for laboratory ventilation equipment based on data analysis, characterized in that: It includes emission operation acquisition module, environmental parameter acquisition module, emission environment corrosion analysis module, emission volume analysis module, data fusion analysis module, emission volume analysis module and data service platform; The emission operation collection module collects the operating parameters of each ventilation device in the laboratory, and sends the collected operating parameters of each ventilation device to the emission analysis module; The environmental parameter collection module includes several environmental parameter collection units, which collect the concentration of various gas types in the environment in the area in real time; The emission environment corrosion analysis module extracts the gas concentration corresponding to each type of gas emitted cumulatively by each ventilation device, the emission time, and the humidity and temperature values ​​in the ventilation device corresponding to each type of gas emitted, analyzes the corrosion acceleration damage coefficient of each gas type on the ventilation device in the emission environment, and sends the analyzed corrosion acceleration damage coefficient of each gas type on the ventilation device to the data fusion analysis module; The emission analysis module obtains the operating parameters of the ventilation equipment in each area collected by the emission operation collection module, extracts the working power of the ventilation equipment in the operating parameters, and selects the theoretical emission gas volume LQ corresponding to the ventilation equipment power per unit time T according to the working power of the ventilation equipment; The data fusion analysis module extracts the estimated accelerated damage coefficient of corrosion of each gas type on the ventilation equipment, performs data prediction fusion processing on the estimated accelerated damage coefficient of corrosion of each gas type on the ventilation equipment and the duration of each gas type previously discharged by the laboratory, predicts the predicted duration corresponding to the ventilation equipment reaching the set exhaust duct leakage diameter threshold from the current state, and feeds back the analyzed predicted duration to the data service platform; The data service platform extracts the predicted time corresponding to the ventilation equipment reaching the set exhaust duct leakage diameter threshold from the current state sent by the data fusion analysis module, and extracts the emission time and emission gas concentration of each gas type in the sampling time period in real time. Combined with the average value SQ of the actual emission gas volume of the ventilation equipment in the sampling time period, the error offset of the predicted time is calculated, and the error offset is used to dynamically adjust the predicted time. The emission environment corrosion analysis module analyzes the estimated corrosion damage coefficient of each gas type on the ventilation equipment within a fixed monitoring time period, including the following steps: Step A1, extract the ventilation equipment for acidic, alkaline and corrosive gases to reach the gas concentration when the emission conditions and the temperature, humidity and emission time during the emission process, to establish a gas emission matrix L; Step A2, extracting the gas concentration of each gas type and the time required for the gas to be completely discharged recorded in the gas emission matrix, and analyzing the gas emission concentration decay rate; Step A3, using a corrosion damage prediction model to analyze the corrosion acceleration damage coefficient of each gas type discharged from the ventilation equipment on the ventilation equipment; The formula of the corrosion damage prediction model is: , Pi is the estimated accelerated damage coefficient of corrosion of ventilation equipment under the interference of the i-th exhaust gas, is the unit gas concentration of the i-th gas type, in mg / m3, is the corrosion ratio coefficient corresponding to the unit gas concentration of the i-th gas type, in m3 / mg. For the set standard humidity, is the set standard temperature, xi1 is the gas concentration corresponding to the i-th gas type under the exhaust condition of the ventilation equipment, xi4 is the time required for the i-th gas type to be discharged through the ventilation equipment, and Vi is the exhaust concentration decay rate of the i-th gas type.

2. A fault prediction system for laboratory ventilation equipment based on data analysis according to claim 1, characterized in that: The emission analysis module also extracts the wind speed V from the operating parameters, uses the wind volume calculation formula to analyze the actual emission gas volume of the ventilation equipment per unit time, analyzes the theoretical emission gas volume and the actual emission gas volume SQ, and obtains the gas emission attenuation coefficient.

3. The fault prediction system for laboratory ventilation equipment based on data analysis according to claim 1, characterized in that: The data fusion analysis module uses the data prediction fusion formula in the process of data prediction fusion processing: , is the average value of the theoretical exhaust gas volume of the ventilation equipment at different working frequencies, is the average value of the actual exhaust gas volume of the ventilation equipment at different working frequencies at the current moment, It is the average value of the actual amount of gas emitted at different working frequencies when the ventilation equipment reaches the set threshold of the exhaust duct leakage diameter, so as to eliminate the large deviation of the predicted duration caused by the different working frequencies of the ventilation equipment, and improve the prediction of the sustainable emission duration of the gas. E is the predicted sustainable emission duration of the gas, e is a natural number, and ui is the total emission duration of the i-th gas type in the laboratory in the past.

4. A fault prediction system for laboratory ventilation equipment based on data analysis according to claim 3, characterized in that: The calculation formula for the error offset of the prediction duration is: , e is a natural number, is the gas concentration required to be emitted by the i-th gas type during the sampling period, is the emission duration of the i-th gas type during the sampling period, is the average emission rate of the i-th gas type emitted by the ventilation equipment in the past at the predicted sustainable emission duration E, is the error offset coefficient of the prediction duration.

5. A fault prediction system for laboratory ventilation equipment based on data analysis according to any one of claims 1 to 4, characterized in that: The fault prediction system of the laboratory ventilation equipment also includes a fault emission training module, which extracts the actual emission gas volume of the ventilation equipment at different operating frequencies under different fault types and the theoretical emission gas volume under different operating frequencies, performs decentralized training on the actual emission gas volume under each fault type under the same operating frequency, obtains the standardization of the actual emission gas volume after decentralized training, and analyzes the emission output interference measurement corresponding to each fault type.

6. A fault prediction system for laboratory ventilation equipment based on data analysis according to claim 5, characterized in that: The actual emission gas volume of different fault types under the same working frequency is dispersedly trained. The specific training method is as follows: Step 1: extract the actual emission gas volume of different fault types under the same working frequency, and the number of times the actual emission gas volume of each fault type is extracted is the same, that is, the number of samples extracted for the same fault type under the same working frequency is f; Step 2: Establish a sample training feature table; Step 3: Standardize the actual exhaust gas volume corresponding to each fault type to obtain standardized training samples , , k is the total number of samples, k=C*N*f, C is the number of working frequencies of the ventilation equipment, that is, frequency 1, frequency 2, frequency 3, C takes the value of 3, N is the number of fault types, is the actual emission gas volume corresponding to the jth sample in the sample training feature table; Step 4: extract standard training samples corresponding to different fault types under the same operating frequency; Step 5: The emission output interference measurement model is used to analyze the emission output interference measurement corresponding to each fault type, which can accurately eliminate the dynamic interference degree of the fault type on the exhaust condition of the ventilation equipment under the working frequency interference.

7. A fault prediction system for laboratory ventilation equipment based on data analysis according to claim 6, characterized in that: The formula of the emission output interference measurement model in step 5 is: , is the exhaust output interference measure corresponding to the cth fault type, is the exhaust weight proportional coefficient corresponding to the cth fault type, , z is equal to 1, 2, 3, c is 1, 2, ..., N, which is the actual exhaust gas volume corresponding to the cth fault type of the ventilation equipment at the zth working frequency, is the actual exhaust gas volume corresponding to the cth fault type of the ventilation equipment at the zth operating frequency, and .

Images