Corona ion source stability identification method, device, equipment, medium and product

Abstract

The invention relates to the technical field of substance analysis, and discloses a corona ion source stability identification method, device and equipment, a medium and a product, and the method comprises the steps: obtaining target equipment parameters; the target equipment parameters are acquired when the temperature and humidity of the corona ion source reach a constant state; calculating corona onset voltage according to the target equipment parameters; the corona onset voltage is used for electrifying the corona ion source; and acquiring spectrogram information corresponding to the corona ion source, identifying the spectrogram information through the neural network model, and acquiring an identification result of corona onset stability of the corona ion source. According to the scheme, in a stable environment, each parameter of the corona ion source is integrally considered through the neural network model, and the accuracy of stability identification of the corona ion source is improved.

Description

Technical Field

[0001] The invention relates to the technical field of material analysis, and in particular to a corona ion source stability identification method, device, equipment, medium and product. Background Art

[0002] Mass spectrometry and ion mobility spectrometry are methods used to detect characteristic information of ions. A corona ion source uses AC high voltage or DC pulse high voltage to discharge into the air to generate charged ions. The generation of charged ions is a process from nothing to something, so the stability of ions generated by a corona ion source is particularly important.

[0003] Different from the radioactive source that ionizes the air to produce ions, the stability of the corona ion source depends on many factors, such as the intensity U and frequency H of the AC voltage, the temperature T of the air, the humidity Q of the air, the distance S between the positive and negative electrodes, the radius of curvature R of the discharge needle, etc. The abnormality of various factors will cause the ion source to not work properly. Therefore, since the stability of the corona ion source is affected by many factors, the accuracy of identifying the stability of the corona ion source by detecting various factors is low. Summary of the invention

[0004] In view of this, the present invention provides a corona ion source stability identification method, device, system, equipment and medium to improve the accuracy of identifying the stability of the corona ion source.

[0005] In a first aspect, the present invention provides a method for identifying the stability of a corona ion source, the method comprising: obtaining target device parameters; the target device parameters are collected when the temperature and humidity of the corona ion source reach a constant state; calculating a corona inception voltage according to the target device parameters; the corona inception voltage is used to power on the corona ion source; obtaining spectral information corresponding to the corona ion source, and identifying the spectral information through a neural network model to obtain an identification result of the corona inception stability of the corona ion source.

[0006] In a possible implementation, the method further includes: if the recognition result indicates instability, adjusting the corona inception voltage until the recognition result is stable.

[0007] In a possible implementation, the spectrum information includes environmental parameters, injection information, and signal characteristics.

[0008] In one possible implementation, the environmental parameters include at least one of temperature, humidity and gas flow; the injection information includes at least one of solvent, detection substance, concentration and injection volume; the signal characteristics include at least one of the maximum value, mean, variance, half-peak width, peak position, peak width, peak height, peak area and symmetry of each ion signal.

[0009] In a possible implementation, the constant state is that the temperature change value ΔT of the corona ion source within a time range of 1 s is ≤0.1° C., and the humidity change value ΔQ of the corona ion source within a time range of 1 s is ≤0.1%.

[0010] In one possible implementation, the method also includes: obtaining a sample data set; the sample data set includes corresponding sample spectrogram information and sample annotations; inputting the sample spectrogram information into a neural network model for processing to obtain a prediction result; and updating the neural network model through a back propagation algorithm based on the error between the prediction result and the sample annotation.

[0011] In a second aspect, the present invention provides a device for identifying the stability of a corona ion source, the device comprising: a parameter acquisition module, used to acquire target device parameters; the target device parameters are collected when the temperature and humidity of the corona ion source reach a constant state; a voltage calculation module, used to calculate the corona inception voltage according to the target device parameters; the corona inception voltage is used to power on the corona ion source; a result identification module, used to acquire spectral information corresponding to the corona ion source, and identify the spectral information through a neural network model to obtain an identification result of the corona inception stability of the corona ion source.

[0012] In a possible implementation, the result recognition module is further configured to: if the recognition result indicates instability, adjust the corona inception voltage until the recognition result becomes stable.

[0013] In a possible implementation, the spectrum information includes environmental parameters, injection information, and signal characteristics.

[0014] In one possible implementation, the environmental parameters include at least one of temperature, humidity and gas flow; the injection information includes at least one of solvent, detection substance, concentration and injection volume; the signal characteristics include at least one of the maximum value, mean, variance, half-peak width, peak position, peak width, peak height, peak area and symmetry of each ion signal.

[0015] In a possible implementation, the constant state is that the temperature change value ΔT of the corona ion source within a time range of 1 s is ≤0.1° C., and the humidity change value ΔQ of the corona ion source within a time range of 1 s is ≤0.1%.

[0016] In one possible implementation, the device also includes: a sample acquisition module for acquiring a sample data set; the sample data set includes corresponding sample spectrogram information and sample annotations; a prediction module for inputting the sample spectrogram information into a neural network model for processing to obtain a prediction result; and an update module for updating the neural network model through a back propagation algorithm based on the error between the prediction result and the sample annotation.

[0017] In a third aspect, a computer device is provided, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the above-mentioned corona ion source stability identification method by executing the computer instructions.

[0018] In a fourth aspect, a computer-readable storage medium is provided, on which computer instructions are stored, and the computer instructions are used to enable a computer to execute the above-mentioned corona ion source stability identification method.

[0019] In a fifth aspect, a computer program product is provided, comprising computer instructions for causing a computer to execute the above-mentioned corona ion source stability identification method.

[0020] The technical solution provided by this application may have the following beneficial effects:

[0021] The present application can collect target device parameters when the temperature and humidity of the corona ion source reach a constant state, and calculate the corona inception voltage according to the target device parameters; the corona inception voltage is used to power on the corona ion source; then the computer device obtains the spectrum information corresponding to the corona ion source, and identifies the spectrum information through a neural network model to obtain the identification result of the corona inception stability of the corona ion source. The above scheme calculates the corona inception voltage based on the parameters collected when the temperature and humidity of the corona ion source reach a constant state, so as to power on the corona ion source, and identifies the spectrum information at this time through a neural network model, so that in a stable environment, the various parameters of the corona ion source are considered as a whole through the neural network model, thereby improving the accuracy of identifying the stability of the corona ion source. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0023] Figure 1 A structural schematic diagram of a stability identification system for a corona ion source involved in an embodiment of the present application is shown.

[0024] Figure 2 The present invention is a method flow chart of a method for identifying the stability of a corona ion source according to an exemplary embodiment.

[0025] Figure 3 The present invention is a method flow chart of a method for identifying the stability of a corona ion source according to an exemplary embodiment.

[0026] Figure 4 A model structure diagram of a neural network model involved in an embodiment of the present application is shown.

[0027] Figure 5 A detection flow chart involved in an embodiment of the present application is shown.

[0028] Figure 6 This is a schematic diagram of the structure of a corona ion source stability identification device provided in an embodiment of the present application.

[0029] Figure 7 It is a structural schematic diagram of a computer device provided by an optional embodiment of the present invention. DETAILED DESCRIPTION

[0030] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are 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 those skilled in the art without creative work are within the scope of protection of the present invention.

[0031] In the description of the embodiments of the present application, the term "corresponding" may indicate a direct or indirect correspondence between two items, or an association relationship between the two items, or a relationship between indication and being indicated, configuration and being configured, and the like.

[0032] Mass spectrometry and ion mobility spectrometry are methods used to detect ion characteristic information. Ion sources are needed to generate ions, and there are many ways to generate ions, such as ionizing air with a radioactive source, ionizing air with ultraviolet light, and ionizing air with high voltage. A corona ion source uses AC high voltage or DC pulse high voltage to discharge air to generate charged ions. Charged ions are a process from scratch, so the stability of ions generated by a corona ion source is particularly important.

[0033] In the related technology, using a radioactive source to ionize the air can stably obtain charged ions, but the radioactive source is strictly regulated and the cost is high. Using a corona ion source is low-cost and does not require additional supervision; but the stability is poor.

[0034] Different from the radioactive source that ionizes the air to produce ions, the stability of the corona ion source depends on many factors, such as the intensity U and frequency H of the AC voltage, the temperature T of the air, the humidity Q of the air, the distance S between the positive and negative electrodes for discharge, the radius of curvature R of the discharge needle, etc. For example, when the intensity U of the AC voltage is too low, it cannot break through the air, and thus cannot ionize the air; when the frequency H of the AC voltage is too low, it cannot form a rapidly changing alternating electric field, and thus cannot break through the air, and thus cannot ionize the air; when the temperature T of the air is low, the movement speed of the air molecules is low, and a higher AC voltage U is required to break through the air. However, when the AC voltage U is too high, it will also affect the stability of the corona ion source, mainly because if the AC voltage U is too high, the discharge capacity of the ion source will be too strong, causing the ion source to burn out and unable to produce ions normally.

[0035] The main phenomenon of the corona ion source is that the data detected by the detector is transmitted to the display end, and the phenomenon presented is that the height, half-peak width and other information of the main ion spectrum peak present a relatively stable state. When no specific substance is detected, the spectrum information will not change dramatically, such as the height L of each ion peak in the spectrum. i The total area of ​​the ion peak fluctuates within a certain range, and the change in the total area of ​​the ion peak is less than 20%. When the substance is detected, the type of the main ion changes, causing the main ion spectrum peak L i The changes are large, and the peak heights of different ions show an increase and decrease phenomenon, and will return to the state of the ion peaks without injection. At the same time, the change range of the total ion peak area is less than 20%. The phenomenon of unstable corona ion source is mainly that the ion peak disappears suddenly, or the change range is irregular, and it cannot be restored to the state without injection, and the total ion peak area changes by more than 20%.

[0036] Please refer to Figure 1 , which shows a schematic diagram of the structure of a stability identification system of a corona ion source involved in an embodiment of the present application. Figure 1 As shown, the system includes a corona ion source 110 and a computer device 120 .

[0037] Optionally, the computer device 120 can be loaded with an AI processing platform. In this case, the user can transmit the ion spectrum of the corona ion source to the computer device 120 through the terminal device 110 via a wired or wireless network. The computer device 120 will process the ion spectrum through the AI ​​processing platform to determine the stability of the corona ion source.

[0038] Optionally, the computer device may be a personal computer with high computing power; or the computer device may be a server with high computing power.

[0039] Optionally, the above-mentioned server can be a server cluster or a distributed system composed of multiple physical servers, or it can be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), as well as big data and artificial intelligence platforms and other technical computing services.

[0040] Optionally, the system may further include a management device, which is used to manage the system (such as managing the connection status between each module and the server, etc.), and the management device is connected to the server via a communication network. Optionally, the communication network is a wired network or a wireless network.

[0041] Optionally, the above-mentioned wireless network or wired network uses standard communication technology and / or protocol. The network is usually the Internet, but it can also be any other network, including but not limited to any combination of local area network, metropolitan area network, wide area network, mobile, limited or wireless network, private network or virtual private network. In some embodiments, the technology and / or format including hypertext markup language, extensible markup language, etc. are used to represent the data exchanged through the network. In addition, conventional encryption technologies such as secure socket layer, transport layer security, virtual private network, Internet protocol security, etc. can also be used to encrypt all or some links. In other embodiments, customized and / or dedicated data communication technology can also be used to replace or supplement the above-mentioned data communication technology.

[0042] Figure 2 is a method flow chart of a method for identifying the stability of a corona ion source according to an exemplary embodiment. The method is executed by a computer device, which may be Figure 1 Computer equipment in the system shown. Figure 2 As shown, the corona ion source stability identification method may include the following steps:

[0043] Step 201, obtaining target device parameters; the target device parameters are collected when the temperature and humidity of the corona ion source reach a constant state.

[0044] Since the working state of the corona ion source is affected by many factors, in order to determine the stability of the corona ion source, it is first necessary to eliminate the interference of external factors on the corona ion source, that is, when the temperature and humidity of the corona ion source reach a constant state, the target device parameters of the corona ion source are collected.

[0045] In some optional implementations, the temperature and humidity inside the computer device can be brought to a constant state by heating or other means, and after reaching the constant state, the corresponding values ​​reach a relatively stable level.

[0046] Step 202, calculating a corona inception voltage according to the target device parameters; the corona inception voltage is used to power on the corona ion source.

[0047] When the corona ion source collects the target device parameters under constant temperature and humidity, the corona inception voltage of the corona ion source can be calculated according to the target device parameters, that is, the minimum voltage at which the air begins to ionize. Based on the breakdown characteristics of air, the corona inception voltage is a function related to temperature, humidity, electrode spacing, discharge needle curvature radius, etc.

[0048] Step 203, obtaining the spectrum information corresponding to the corona ion source, and identifying the spectrum information through a neural network model to obtain an identification result of the corona initiation stability of the corona ion source.

[0049] After the corona inception voltage is obtained, the corona ion source can be powered on according to the corona inception voltage, so that the air just begins to ionize. At this time, the detector is used to collect the ion spectrum generated by the discharge of the corona ion source. The ion spectrum includes characteristic parameters such as ion peak height, half-peak width, and total area. By identifying and classifying the characteristic parameters in the ion spectrum through the neural network model, it can be determined whether the state of the corona ion source is stable.

[0050] In summary, the present application can collect the target device parameters when the temperature and humidity of the corona ion source reach a constant state, and calculate the corona inception voltage according to the target device parameters; the corona inception voltage is used to power on the corona ion source; then the computer device obtains the spectral information corresponding to the corona ion source, and identifies the spectral information through the neural network model to obtain the identification result of the corona inception stability of the corona ion source. The above scheme calculates the corona inception voltage based on the parameters collected when the temperature and humidity of the corona ion source reach a constant state, so as to power on the corona ion source, and identify the spectral information at this time through the neural network model, so as to improve the accuracy of the identification of the stability of the corona ion source by comprehensively considering the various parameters of the corona ion source through the neural network model in a stable environment.

[0051] Figure 3 is a method flow chart of a method for identifying the stability of a corona ion source according to an exemplary embodiment. The method is executed by a computer device, which may be Figure 1 Computer equipment in the system shown. Figure 3 As shown, the corona ion source stability identification method may include the following steps:

[0052] Step 301, obtaining a sample data set; the sample data set includes corresponding sample spectrogram information and sample annotations.

[0053] In an embodiment of the present application, the sample spectrum information may be ion spectra collected at various historical moments; and the sample annotation may be the result of manually evaluating the stability of the corona ion source at various historical moments.

[0054] Step 302: input the sample spectrogram information into the neural network model for processing to obtain a prediction result.

[0055] Please refer to Figure 4 , which shows a model structure diagram of a neural network model involved in an embodiment of the present application. Figure 4 As shown in the figure, the neural network model includes an input layer X, a hidden layer H, and an output layer Y. The input layer and the hidden layer are connected by neurons with a weight matrix W1; the hidden layer and the output layer are connected by neurons with a weight matrix W2. Among them, x_axis and y_axis in the input layer X represent input information of different dimensions, and ReLu (Rectified Linear Unit) in the hidden layer represents the activation function. Softmax in the input layer Y represents the activation function, and Cross Entropy Error represents the cross entropy loss.

[0056] Step 303: Based on the prediction result and the error between the sample annotations, the neural network model is updated through a back propagation algorithm.

[0057] Optionally, the neural network model is a BP (Back Propagation) neural network model, and the error is obtained through a forward path, and then the error is back-propagated, so that the weights of the weight matrix of the BP neural network model can be corrected.

[0058] Among them, the error of MPL (Multi-Layer Perceptron) can be expressed by a square error function.

[0059] In a practical application, suppose a sample X = (x1, x2, ..., x n ) corresponds to the target value t, which has J possible values, and we can get t=(t1,t2,...,t j ).

[0060] Then the MPL input layer has a total of n neurons, and the output layer (the Lth layer) has J neurons.

[0061] Suppose the final output of sample X after the forward path is

[0062] The subscript indicates the index of the neuron, and the superscript indicates the layer.

[0063] The square error E of the sample is as follows:

[0064]

[0065] in, It is for the convenience of setting the derivative coefficient and does not affect the error variation trend. In some optional implementations, other values ​​can be used instead of

[0066] The goal of MLP is to minimize the square error E of the sample. In some optional implementations, E can be minimized by changing the weight ω.

[0067] In a practical application, the Backprop algorithm is used to change the weight ω to minimize E. The Backprop algorithm is an iterative method that gradually reduces E. The derivative of the error E with respect to the weight ω is the rate of change of ω as shown below:

[0068]

[0069] Among them, Δω(t) represents the rate of change of ω, η∈(0,1) represents the learning efficiency, which controls the convergence speed and accuracy. μ represents momentum, which provides some inertia and can smooth the random fluctuations of weights. t represents the current time, t-1 represents the last time, and t+1 represents the next time.

[0070] The expression for updating the current weight ω by Δω is as follows:

[0071] ω(t+1)=ω(t)+Δω(t)

[0072] The above formula shows that the process of updating weights is from the output layer to the hidden layer, and then to the input layer layer by layer, which is the back propagation of errors.

[0073] When all weights are updated, the new error E is calculated by the forward path, completing one iteration.

[0074] In specific applications, to use neural networks to analyze the stability of data generated by corona ion sources, the following steps can be followed:

[0075] 1. Data preparation: Collect and prepare data samples generated by the corona ion source. The data samples include data in stable and unstable states. Process missing values, outliers, and error values ​​in the data samples to ensure the integrity and accuracy of the data. Standardize and normalize the data to make them have the same dimension and unit to eliminate the dimensional impact between different data and make them suitable for subsequent analysis tasks.

[0076] 2. Feature extraction: Extract meaningful features from the data to describe the shape and dynamic characteristics of the signal, such as environmental parameters (temperature, humidity, gas flow), injection information (solvent, test substance, concentration, injection volume), signal intensity statistical characteristics (maximum value, mean, variance, half-peak width of each ion signal), peak shape (peak position, peak width, peak height, peak area, symmetry, etc.), to distinguish different ion signals and background noise under different working conditions. These features will become the input of the neural network.

[0077] 3. Data partitioning: Divide the dataset into training set, validation set and test set for training and validating the model. Divide the dataset into training set, validation set and test set for training the model, tuning parameters and evaluating model performance. Expand or enhance the data to increase the number of samples and improve the generalization ability of the model. Start executing the algorithm on the training set, select the best model through the validation set or simple cross-validation set, and after sufficient validation, select the final model, which can then be evaluated on the test set.

[0078] In specific applications, in order to evaluate the operation of the algorithm in an unbiased manner, the dataset can be divided into 60% training set, 20% validation set and 20% test set.

[0079] 4. Construct a neural network model: Use a two-layer BP neural network, get the error through the forward path, and then back propagate the error to achieve weight correction. Set the learning step size to 0.01, and use the ReLu function as the activation function. In order to prevent overfitting, in addition to increasing the amount of data, L2 Regularization can also be used.

[0080] 5. Model training: The neural network model is trained using the training set and the model parameters are adjusted to capture the stability patterns of the data as accurately as possible.

[0081] 6. Model evaluation, optimization, and adjustment: Use the test set to evaluate the performance of the model and check its performance on the validation set data to ensure generalization ability. You can obtain the model's accuracy, recall, F1-Score and other evaluation results, and optimize and adjust the model based on the evaluation results. In the specific implementation, you may need to try different neural network structures, hyperparameter adjustments, etc. to achieve model optimization.

[0082] Among them, the accuracy and F1 score are obtained as shown in the following formula:

[0083]

[0084]

[0085] Among them, TP means the prediction is 1, the actual value is 1, and the prediction is correct. FP means the prediction is 1, the actual value is 0, and the prediction is wrong. FN means the prediction is 0, the actual value is 1, and the prediction is wrong. TN means the prediction is 0, the actual value is 0, and the prediction is correct.

[0086] The recall rate refers to the original sample, which means the probability of being predicted as a positive sample among the samples that are actually positive. The recall rate is obtained as shown in the following formula:

[0087]

[0088] After the neural network model is trained, the trained neural network model can be used to predict the test set data (data that the machine has not seen) to evaluate the reliability of the trained model.

[0089] Step 304, obtaining target device parameters; the target device parameters are collected when the temperature and humidity of the corona ion source reach a constant state.

[0090] Specifically, the constant state is that the temperature change value ΔT of the corona ion source within a time range of 1 s is ≤0.1° C., and the humidity change value ΔQ within a time range of 1 s is ≤0.1%.

[0091] Step 305, calculating a corona inception voltage according to the target device parameters; the corona inception voltage is used to power on the corona ion source.

[0092] Step 306, obtaining the spectrum information corresponding to the corona ion source, and identifying the spectrum information through a neural network model to obtain an identification result of the corona initiation stability of the corona ion source.

[0093] Optionally, the spectrum information includes environmental parameters, injection information and signal characteristics.

[0094] Optionally, the environmental parameter includes at least one of temperature, humidity and gas flow. The injection information includes at least one of solvent, detection substance, concentration and injection volume. The signal feature includes at least one of the maximum value, mean, variance, half peak width, peak position, peak width, peak height, peak area and symmetry of each ion signal.

[0095] Step 307: If the recognition result indicates instability, adjust the corona inception voltage until the recognition result is stable.

[0096] Please refer to Figure 5 , which shows a detection flow chart of an embodiment of the present application. Figure 5 As shown, the detection process includes the following steps:

[0097] 1. Start the machine and power on the device.

[0098] 2. Equipment status preparation: In order to reduce the impact of environmental parameters on corona initiation and equipment stability, the equipment uses heating and other means to make the temperature T and humidity Q inside the equipment reach a constant state. After the parameters reach stability, they will no longer change. For example, the temperature T is ΔT≤0.1℃ within the time range of 1s, and the humidity Q is ΔQ≤0.1% within the time range of 1s. If the above requirements are met, proceed to the next step; if not, the equipment continues to be in the preparation stage until the above requirements are met.

[0099] 3. When the equipment is in a stable state, collect the equipment parameters and calculate the corona inception voltage. After the calculation is completed, the equipment powers on the corona ion source according to the calculated value.

[0100] 4. After the corona ion source is powered on, the device reads the spectrum information and makes a judgment using the above algorithm.

[0101] 5. If it is unstable, continue to adjust the parameters until it becomes stable.

[0102] 6. In addition to determining whether the spectrum data is stable during the power-on self-test, the equipment will also analyze the current data in real time during each data collection, completing the equipment's automatic analysis closed loop without the need for staff operation.

[0103] In summary, the present application can collect the target device parameters when the temperature and humidity of the corona ion source reach a constant state, and calculate the corona inception voltage according to the target device parameters; the corona inception voltage is used to power on the corona ion source; then the computer device obtains the spectral information corresponding to the corona ion source, and identifies the spectral information through the neural network model to obtain the identification result of the corona inception stability of the corona ion source. The above scheme calculates the corona inception voltage based on the parameters collected when the temperature and humidity of the corona ion source reach a constant state, so as to power on the corona ion source, and identify the spectral information at this time through the neural network model, so as to improve the accuracy of the identification of the stability of the corona ion source by comprehensively considering the various parameters of the corona ion source through the neural network model in a stable environment.

[0104] In the present application, a kind of corona ion source stability identification device is also provided, and this device is used to realize the above-described embodiment and preferred implementation mode, and the description that has been made will not be repeated. As used below, the term "module" can realize the combination of software and / or hardware of predetermined function. Although the device described in the following embodiments is preferably realized with software, hardware, or the realization of the combination of software and hardware is also possible and conceived.

[0105] The present application embodiment provides a device for identifying the stability of a corona ion source. Figure 6: is a structural schematic diagram of a corona ion source stability identification device provided in an embodiment of the present application, the device comprising:

[0106] The parameter acquisition module 601 is used to acquire the target device parameters; the target device parameters are collected when the temperature and humidity of the corona ion source reach a constant state;

[0107] The voltage calculation module 602 is used to calculate the corona inception voltage according to the target device parameters; the corona inception voltage is used to power the corona ion source;

[0108] The result recognition module 603 is used to obtain the spectrum information corresponding to the corona ion source, and recognize the spectrum information through a neural network model to obtain the recognition result of the corona stability of the corona ion source.

[0109] In a possible implementation, the result identification module is further used to:

[0110] If the identification result indicates instability, adjust the corona inception voltage until the identification result is stable.

[0111] In a possible implementation, the spectrum information includes environmental parameters, injection information, and signal characteristics.

[0112] In one possible implementation, the environmental parameters include at least one of temperature, humidity and gas flow; the injection information includes at least one of solvent, detection substance, concentration and injection volume; the signal characteristics include at least one of the maximum value, mean, variance, half-peak width, peak position, peak width, peak height, peak area and symmetry of each ion signal.

[0113] In a possible implementation, the constant state is that the temperature change value ΔT of the corona ion source within a time range of 1 s is ≤0.1° C., and the humidity change value ΔQ within a time range of 1 s is ≤0.1%.

[0114] In a possible implementation, the device further includes:

[0115] The sample acquisition module is used to acquire a sample data set; the sample data set includes corresponding sample spectrogram information and sample annotations;

[0116] The prediction module is used to input the sample spectrogram information into the neural network model for processing to obtain the prediction result;

[0117] The update module is used to update the neural network model through the back propagation algorithm based on the prediction results and the errors between sample annotations.

[0118] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0119] In summary, the present application can collect the target device parameters when the temperature and humidity of the corona ion source reach a constant state, and calculate the corona inception voltage according to the target device parameters; the corona inception voltage is used to power on the corona ion source; then the computer device obtains the spectral information corresponding to the corona ion source, and identifies the spectral information through the neural network model to obtain the identification result of the corona inception stability of the corona ion source. The above scheme calculates the corona inception voltage based on the parameters collected when the temperature and humidity of the corona ion source reach a constant state, so as to power on the corona ion source, and identify the spectral information at this time through the neural network model, so as to improve the accuracy of the identification of the stability of the corona ion source by comprehensively considering the various parameters of the corona ion source through the neural network model in a stable environment.

[0120] The corona ion source stability identification device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0121] See also Figure 7 , Figure 7 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Figure 7 As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process instructions executed in the computer device, including instructions stored in or on the memory to display graphic information in a graphical user interface on an external input / output device (such as a display device coupled to an interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 7 A processor 10 is taken as an example.

[0122] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0123] The memory 20 stores instructions executable by at least one processor 10, so that at least one processor 10 executes the method shown in the above embodiment.

[0124] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0125] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0126] The computer device further comprises a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0127] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0128] A part of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the existence of the computer program instruction in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc., and accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium accessible to the computer.

[0129] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A method for identifying the stability of a corona ion source, characterized in that: The method comprises: Obtaining target device parameters; the target device parameters are collected when the temperature and humidity of the corona ion source reach a constant state; Calculating a corona inception voltage according to the target device parameters; the corona inception voltage is used to power the corona ion source; Spectral information corresponding to the corona ion source is obtained, and the spectral information is identified through a neural network model to obtain an identification result of the corona initiation stability of the corona ion source.

2. The method according to claim 1, characterized in that: The method further comprises: If the identification result indicates instability, the corona inception voltage is adjusted until the identification result is stable.

3. The method according to claim 1, characterized in that The spectrum information includes environmental parameters, injection information and signal characteristics.

4. The method according to claim 3, characterized in that The environmental parameter includes at least one of temperature, humidity and gas flow rate; The injection information includes at least one of solvent, detection substance, concentration and injection volume; The signal characteristics include at least one of the maximum value, mean value, variance, half peak width, peak position, peak width, peak height, peak area and symmetry of each ion signal.

5. The method according to claim 1, characterized in that The constant state is that the temperature change value ΔT of the corona ion source within a time range of 1 s is ≤0.1° C.; the humidity change value ΔQ of the corona ion source within a time range of 1 s is ≤0.1%.

6. The method according to any one of claims 1 to 4, characterized in that: The method further comprises: Obtaining a sample data set; the sample data set includes corresponding sample spectrogram information and sample annotations; Inputting the sample spectrogram information into the neural network model for processing to obtain a prediction result; Based on the prediction results and the errors between the sample annotations, the neural network model is updated through a back propagation algorithm.

7. A corona ion source stability identification device, characterized in that: The device comprises: A parameter acquisition module, used to acquire target device parameters; the target device parameters are collected when the temperature and humidity of the corona ion source reach a constant state; A voltage calculation module, used for calculating a corona inception voltage according to the target device parameters; the corona inception voltage is used to power the corona ion source; The result recognition module is used to obtain the spectrum information corresponding to the corona ion source, and recognize the spectrum information through a neural network model to obtain the recognition result of the corona stability of the corona ion source.

8. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the corona ion source stability identification method according to any one of claims 1 to 6 by executing the computer instructions.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the corona ion source stability identification method according to any one of claims 1 to 6.

10. A computer program product, characterized in that The method comprises computer instructions for causing a computer to execute the corona ion source stability identification method according to any one of claims 1 to 6.

Images